diff --git a/CLAUDE.md b/CLAUDE.md index a640c2b..ee0db34 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -165,3 +165,5 @@ Dell Pro Max GB10 (product) | Phase | Date | Summary | |-------|------------|------------------------------------------------------| | 1 | 2026-02-14 | Initial knowledge base created from web research | +| 2 | 2026-02-14 | Deep research: NVIDIA docs, reviews, 18 questions resolved | +| 3 | 2026-02-14 | Dell Owner's Manual (Rev A01) integrated, critical corrections applied | diff --git a/context/ai-frameworks.md b/context/ai-frameworks.md index 2397be4..e232fc6 100644 --- a/context/ai-frameworks.md +++ b/context/ai-frameworks.md @@ -2,10 +2,10 @@ id: ai-frameworks title: "AI Frameworks and Development Tools" status: established -source_sections: "Web research: NVIDIA newsroom, Arm learning paths" +source_sections: "Web research: NVIDIA newsroom, Arm learning paths, NVIDIA DGX Spark User Guide" related_topics: [dgx-os-software, gb10-superchip, ai-workloads] key_equations: [] -key_terms: [pytorch, nemo, rapids, cuda, ngc, jupyter, tensorrt, llama-cpp] +key_terms: [pytorch, nemo, rapids, cuda, ngc, jupyter, tensorrt, llama-cpp, docker, nvidia-container-runtime, fex] images: [] examples: [] open_questions: @@ -55,10 +55,12 @@ The Dell Pro Max GB10 supports a broad AI software ecosystem, pre-configured thr ## 3. Development Environment -- **Jupyter Notebooks** — pre-installed for interactive development +- **DGX Dashboard** — web-based system monitor with integrated JupyterLab (T0 Spec) - **Python** — system Python with AI/ML package ecosystem - **NVIDIA NGC Catalog** — library of pre-trained models, containers, and SDKs -- **Containers** — Docker/container support for reproducible environments +- **Docker + NVIDIA Container Runtime** — pre-installed for containerized workflows (T0 Spec) +- **NVIDIA AI Enterprise** — enterprise-grade AI software and services +- **Tutorials:** https://build.nvidia.com/spark ## 4. Software Compatibility Notes @@ -67,7 +69,9 @@ Since the GB10 is an ARM system: - All Python packages must have ARM64 wheels or be compilable from source - Most popular ML libraries (PyTorch, NumPy, etc.) have ARM64 support - Some niche packages may require building from source -- x86-only binary packages will not work +- x86-only binary packages will not run natively +- **FEX emulator** can translate x86 binaries to ARM at a performance cost (used for Steam/Proton gaming — see [[ai-workloads]]) +- Container images must be ARM64/aarch64 builds ## Key Relationships diff --git a/context/ai-workloads.md b/context/ai-workloads.md index 2a694d7..1a5a0fa 100644 --- a/context/ai-workloads.md +++ b/context/ai-workloads.md @@ -2,14 +2,14 @@ id: ai-workloads title: "AI Workloads and Model Capabilities" status: established -source_sections: "Web research: NVIDIA newsroom, Dell product page, WCCFTech" +source_sections: "Web research: NVIDIA newsroom, Dell product page, WCCFTech, Jeff Geerling, ServeTheHome, Tom's Hardware" related_topics: [gb10-superchip, memory-and-storage, ai-frameworks, multi-unit-stacking] key_equations: [model-memory-estimate] key_terms: [llm, inference, fine-tuning, quantization, fp4, fp8, fp16, parameter-count] images: [] examples: [llm-memory-estimation.md] open_questions: - - "Actual tokens/sec benchmarks for common models (Llama 3.3 70B, Mixtral, etc.)" + - "Tokens/sec for Llama 3.3 70B specifically (only 3B and GPT-OSS-120B benchmarked so far)" - "Maximum batch size for inference at various model sizes" - "Fine-tuning performance — how long to SFT a 7B model on this hardware?" - "Stable Diffusion / image generation performance" @@ -23,9 +23,23 @@ The Dell Pro Max GB10 is designed primarily for **local AI inference and fine-tu ## 1. Headline Capabilities - **Up to 200 billion parameter models** locally (with quantization) -- **1 PFLOP (1,000 TFLOPS)** at FP4 precision +- **1 PFLOP (1,000 TFLOPS)** at FP4 precision with sparsity - **Llama 3.3 70B** confirmed to run locally (single unit) -- **Up to 400B parameter models** with two-unit stacking (see [[multi-unit-stacking]]) +- **Up to 405B parameter models** with two-unit stacking (see [[multi-unit-stacking]]) + +## 1a. Measured Performance (T2 Benchmarked) + +| Model / Workload | Performance | Precision | Source | +|-----------------------|-------------------|-----------|----------------| +| Llama 3.2 3B | ~100 tokens/sec | — | Jeff Geerling | +| GPT-OSS-120B | ~14.5 tokens/sec | INT4 | ServeTheHome | +| Llama 3.1 70B | Competitive w/ Ryzen AI Max+ 395 | — | Jeff Geerling | +| HPL (Linpack) FP64 | ~675 GFLOPS | FP64 | Jeff Geerling | +| Geekbench 6 | Comparable to Ryzen AI Max+ 395; trails Apple M3 Ultra | — | Jeff Geerling | + +**Prompt processing** is noted as a particular strength of the system (T2, Jeff Geerling). + +**INT4 inference** on GPT-OSS-120B is roughly equivalent to an RTX 5070's performance (T2, ServeTheHome). ## 2. Model Size vs. Memory @@ -62,6 +76,13 @@ With 128 GB of unified memory, the system can hold: - Large-scale data processing - Graph analytics +### Gaming (bonus, not primary use case) +Surprisingly, ARM Linux gaming works via FEX (x86-to-ARM translation) + Steam/Proton: +- Cyberpunk 2077: ~100 fps at 1080p, low settings (T2, Jeff Geerling) +- Doom Eternal: ~200 fps (T2, Jeff Geerling) + +**Not recommended as a gaming machine** — this is a development tool, not a GeForce. + ## 4. Target Users - AI researchers and developers diff --git a/context/connectivity.md b/context/connectivity.md index 679a134..7ba63ec 100644 --- a/context/connectivity.md +++ b/context/connectivity.md @@ -2,57 +2,77 @@ id: connectivity title: "Connectivity and Networking" status: established -source_sections: "Web research: Dell product page, WCCFTech, Phoronix" +source_sections: "Web research: Dell product page, WCCFTech, Phoronix, NVIDIA DGX Spark User Guide, ServeTheHome, Jeff Geerling" related_topics: [gb10-superchip, multi-unit-stacking, physical-specs, setup-and-config] key_equations: [] key_terms: [usb-c, hdmi, connectx-7, smartnic, qsfp, wifi-7, bluetooth, displayport-alt-mode, 10gbe] images: [] examples: [] open_questions: - - "Which USB-C ports support DisplayPort Alt Mode (all or specific ones)?" - - "Maximum display resolution and refresh rate via HDMI 2.1b and DP Alt Mode" - - "Can the QSFP ports be used for general networking or only for multi-unit stacking?" + - "Can USB-C ports drive multiple displays simultaneously via MST? (Manual says 'Not supported')" --- # Connectivity and Networking The Dell Pro Max GB10 provides extensive I/O for a system of its size, including high-speed networking for multi-unit configurations. +**NOTE: All ports and connectors are located on the BACK of the computer.** The front has no ports. (T0 Spec, Dell Owner's Manual) + +### Rear Panel Layout (left to right) +1. Power button +2. Power-in USB-C port (280W adapter) +3. Three USB 3.2 Gen 2x2 Type-C ports (with DP 1.4a alt-mode, power out) +4. HDMI 2.1a port +5. RJ45 10GbE Ethernet port +6. Two QSFP 200 Gbps ports + ## 1. USB Ports -- **1x USB Type-C (20 Gbps)** — power input port (280W adapter connects here) -- **3x USB Type-C (20 Gbps)** — general purpose -- USB-C ports support **DisplayPort Alt Mode** for display output +- **1x USB Type-C (20 Gbps)** — power input port (280W adapter on Dell, 240W on Spark) +- **3x USB Type-C (20 Gbps)** — USB 3.2 Gen 2x2 with **DisplayPort 1.4a alt-mode** and **power out** +- **Max resolution per USB-C:** 7680 x 4320 at 60 Hz (8K@60) with Type-C to DP adapter (T0 Spec) +- **MST (Multi-Stream Transport):** Not supported (T0 Spec, Dell Owner's Manual) +- **Cable recommendation:** Connect right to left due to port proximity; use standard cables ≤6.5mm width/thickness (T1, Dell Owner's Manual) ## 2. Display Output -- **1x HDMI 2.1b** — dedicated display output -- **USB-C DisplayPort Alt Mode** — additional display(s) via USB-C +- **1x HDMI 2.1a** — dedicated display output (T0 Spec, Dell Owner's Manual) + - **Max resolution:** 7680 x 4320 at 30 Hz (8K@30) (T0 Spec) +- **USB-C DisplayPort 1.4a Alt Mode** — up to 8K@60 per port (T0 Spec) + +**Known issue:** Some displays have compatibility issues, particularly over USB-C/DisplayPort. If no display appears on USB-C, try HDMI instead. (T1 Documented, NVIDIA DGX Spark User Guide; T2 Confirmed, ServeTheHome) ## 3. Wired Networking -- **1x 10 GbE Ethernet** (RJ45) — standard network connectivity -- **2x QSFP 200 Gbps ports** — via NVIDIA ConnectX-7 SmartNIC - - Each port supports 200 Gbps +- **1x 10 GbE Ethernet** (RJ45, **Realtek RTL8127-CG** controller) — standard network connectivity (T0 Spec) +- **2x QSFP56 200 Gbps ports** — via NVIDIA ConnectX-7 SmartNIC + - Each port: 4 channels of 56G/50Gbps PAM4 (T0 Spec) + - Connected via x4 PCIe Gen 5 links (T2, Jeff Geerling) + - **Ethernet configuration only** — no InfiniBand (T1 Documented, NVIDIA DGX Spark User Guide) - Primary use: [[multi-unit-stacking]] for scaling to 2-unit configurations - - Based on ConnectX-7 SmartNIC technology + - Can be used for general 200GbE networking + - Real-world throughput: ~106 Gbps single stream, 200+ Gbps with RDMA (T2, Jeff Geerling) ## 4. Wireless -- **Wi-Fi 7** (IEEE 802.11be) +- **Module:** AzureWave AW-EM637 (T0 Spec, Dell Owner's Manual) +- **Wi-Fi 7** (802.11be) — also supports 802.11a/b/g, Wi-Fi 4 (n), Wi-Fi 5 (ac), Wi-Fi 6E (ax) +- **Frequency bands:** 2.4 GHz / 5 GHz / 6 GHz +- **Max transfer rate:** Up to 1000 Mbps - **Bluetooth 5.4** +- **Encryption:** 128-bit AES-CCMP, 256-bit AES-GCMP, 256-bit AES-GMAC ## 5. Port Summary Table -| Port | Count | Speed/Spec | Notes | -|--------------------|-------|----------------|--------------------------| -| USB-C (power) | 1 | 20 Gbps | 280W power delivery | -| USB-C (data) | 3 | 20 Gbps | DP Alt Mode supported | -| HDMI | 1 | 2.1b | Display output | -| RJ45 Ethernet | 1 | 10 GbE | Standard networking | -| QSFP | 2 | 200 Gbps each | ConnectX-7 SmartNIC | -| Wi-Fi | 1 | Wi-Fi 7 | 802.11be | -| Bluetooth | 1 | 5.4 | Integrated | +| Port | Count | Speed/Spec | Max Resolution / Notes | +|--------------------|-------|-------------------|-------------------------------------| +| USB-C (power) | 1 | 20 Gbps | 280W PD (Dell) / 240W (Spark) | +| USB-C (data) | 3 | 20 Gbps Gen2x2 | DP 1.4a: 8K@60, power out | +| HDMI | 1 | 2.1a | 8K@30 (7680x4320) | +| RJ45 Ethernet | 1 | 10 GbE | Realtek RTL8127-CG | +| QSFP56 | 2 | 200 Gbps each | ConnectX-7, Ethernet only | +| Wi-Fi | 1 | Wi-Fi 7 (1 Gbps) | AzureWave AW-EM637, 2.4/5/6 GHz | +| Bluetooth | 1 | 5.4 | Paired with Wi-Fi in UEFI | ## Key Relationships diff --git a/context/dgx-os-software.md b/context/dgx-os-software.md index 18cd1ad..5582c5d 100644 --- a/context/dgx-os-software.md +++ b/context/dgx-os-software.md @@ -2,17 +2,16 @@ id: dgx-os-software title: "DGX OS and System Software" status: established -source_sections: "Web research: NVIDIA DGX OS 7 User Guide, Dell support articles, Phoronix" +source_sections: "Web research: NVIDIA DGX OS 7 User Guide, Dell support articles, Phoronix, NVIDIA DGX Spark User Guide, ServeTheHome" related_topics: [ai-frameworks, setup-and-config, gb10-superchip] key_equations: [] -key_terms: [dgx-os, ubuntu, cuda, nvidia-driver, dgx-spark, kernel] +key_terms: [dgx-os, ubuntu, cuda, nvidia-driver, dgx-spark, kernel, nvidia-sync, dgx-dashboard, fwupdmgr, ai-enterprise] images: [] examples: [] open_questions: - "Can a stock Ubuntu 24.04 ARM be installed instead of DGX OS?" - - "Full list of pre-installed NVIDIA packages and versions" - - "OTA update mechanism and cadence for DGX OS" - - "Does DGX OS include Docker/container runtime by default?" + - "Full list of pre-installed NVIDIA packages and exact versions" + - "Update cadence and EOL timeline details beyond the 2-year guarantee" --- # DGX OS and System Software @@ -38,12 +37,16 @@ DGX OS is not a separate distribution — it is Ubuntu 24.04 with NVIDIA's custo The system ships ready to run AI workloads with: -- **CUDA toolkit** — GPU compute API and compiler +- **CUDA toolkit + cuDNN** — GPU compute API, compiler, and deep learning primitives - **NVIDIA drivers** — optimized for GB10 Blackwell GPU +- **Docker + NVIDIA Container Runtime** — container support out of the box (T0 Spec) +- **NVIDIA Sync** — application management and configuration tool +- **DGX Dashboard** — system monitoring with integrated JupyterLab +- **NGC** — access to NVIDIA GPU Cloud containerized applications and models +- **AI Enterprise** — enterprise-grade AI software assets and services - **Python** — system Python plus development environments - **GCC** — ARM-native compiler toolchain - **OpenJDK** — Java runtime -- **Jupyter notebooks** — interactive development environment For AI frameworks, see [[ai-frameworks]]. @@ -68,11 +71,35 @@ Dell provides a documented process for reinstalling DGX OS: Source: [Dell Support KB Article](https://www.dell.com/support/kbdoc/en-us/000382042/how-to-reinstall-the-nvidia-dgx-operating-system-on-dell-pro-max-with-grace-blackwell-systems) -## 5. Important Notes +## 5. Firmware Updates + +Dell and NVIDIA use **different firmware signing keys**. Dell units require Dell-signed firmware payloads, not generic DGX Spark firmware. (T1 Documented, ServeTheHome) + +### Update Procedure + +```bash +sudo apt update +sudo apt upgrade +sudo fwupdmgr refresh +sudo fwupdmgr upgrade +``` + +The GUI alternative: DGX Dashboard → Settings → Update (triggers reboot for BIOS/firmware changes). + +Firmware updates take approximately 1-2 minutes plus a reboot. + +## 6. Support Lifecycle + +- **Guaranteed updates:** 2 years from purchase (T2, Jeff Geerling) +- **Support channel:** Dell provides support for Dell Pro Max units (not NVIDIA directly) +- **Implication:** Dell partners provide ongoing firmware and support, distinct from NVIDIA's DGX Spark support + +## 7. Important Notes - **ARM-only:** All software must be ARM64/aarch64 compatible. x86 binaries will not run natively. - **No Windows:** This system does not support Windows installation. - **Package management:** Standard Ubuntu `apt` package manager, plus NVIDIA's own repositories. +- **NVIDIA kernel:** The system requires NVIDIA's specific kernel for full hardware compatibility. ## Key Relationships diff --git a/context/equations-and-bounds.md b/context/equations-and-bounds.md index 471203a..e5cf695 100644 --- a/context/equations-and-bounds.md +++ b/context/equations-and-bounds.md @@ -23,16 +23,21 @@ Reference for all quantitative specifications, formulas, and validation ranges f | Precision | Peak TFLOPS | Source | Notes | |-----------|-------------|----------|------------------------------------| -| FP4 | 1,000 | T0 Spec | Headline figure, 1 PFLOP | +| FP4 | 1,000 | T0 Spec | Headline figure, 1 PFLOP (w/ sparsity) | | FP8 | ~500 | T3 Infer | Typical 2:1 ratio from FP4 | | FP16 | ~250 | T3 Infer | Typical 4:1 ratio from FP4 | | FP32 | ~125 | T3 Infer | Typical 8:1 ratio from FP4 | +| FP64 | ~0.675 | T2 Bench | HPL Linpack, Jeff Geerling | -*Note: FP8/FP16/FP32 values are inferred from typical Blackwell architecture ratios. Actual values not yet independently confirmed.* +*Note: FP8/FP16/FP32 values are inferred from typical Blackwell architecture ratios. FP64 is benchmarked. FP4 headline includes sparsity.* ### GPU Cores - **CUDA cores:** 6,144 (T0 Spec) - **Tensor Cores:** 5th generation (count TBD) +- **RT Cores:** 4th generation (T0 Spec) +- **Copy engines:** 2 (T0 Spec) +- **NVENC:** 1 (T0 Spec) +- **NVDEC:** 1 (T0 Spec) ## 2. Memory @@ -40,6 +45,9 @@ Reference for all quantitative specifications, formulas, and validation ranges f - **Memory bandwidth:** 273 GB/s (T0 Spec, LPDDR5X at 9,400 MT/s) - **NVLink-C2C bandwidth:** 600 GB/s bidirectional (T0 Spec, CPU-GPU interconnect) +### Configuration +- **Interface:** 256-bit, 16 channels LPDDR5X 8533 (T0 Spec, NVIDIA DGX Spark User Guide) + ### Capacity - **Total unified memory:** 128 GB LPDDR5X (T0 Spec) - **Usable for models:** ~109-115 GB (T3 Infer, after OS/framework/KV cache overhead) @@ -78,24 +86,42 @@ Rule of thumb: budget **1.2-1.5x** the raw model weight size for total inference ## 4. Networking Bounds -| Interface | Bandwidth | Direction | -|---------------------|--------------------|-----------------| -| NVLink-C2C | 600 GB/s | Bidirectional | -| LPDDR5X memory | 273 GB/s | System memory | -| QSFP (per port) | 200 Gbps (25 GB/s) | Network | -| QSFP (total) | 400 Gbps (50 GB/s) | 2 ports combined| -| 10 GbE Ethernet | 10 Gbps (1.25 GB/s)| Network | -| USB-C (per port) | 20 Gbps (2.5 GB/s) | I/O | +| Interface | Spec Bandwidth | Measured | Direction | +|---------------------|--------------------|-------------------|-----------------| +| NVLink-C2C | 600 GB/s | — | Bidirectional | +| LPDDR5X memory | 273 GB/s | — | System memory | +| QSFP (per port) | 200 Gbps (25 GB/s) | ~106 Gbps single stream | Network | +| QSFP (total) | 400 Gbps (50 GB/s) | 200+ Gbps RDMA | 2 ports combined| +| QSFP PCIe link | x4 PCIe Gen 5 | — | Internal | +| 10 GbE Ethernet | 10 Gbps (1.25 GB/s)| — | Network | +| USB-C (per port) | 20 Gbps (2.5 GB/s) | — | I/O | -## 5. Power Bounds +*QSFP measured throughput from Jeff Geerling (T2 Benchmarked).* -| Parameter | Value | -|---------------------|---------| -| PSU rating | 280W | -| System TDP | ~140W | -| Power delivery | USB-C PD| +## 5. Power Bounds -## 6. Physical Bounds +| Parameter | Dell Pro Max | DGX Spark | Source | +|-------------------------|-------------|-----------|-------------| +| PSU rating | 280W | 240W | T0 Spec | +| GPU TDP | 140W | 140W | T0 Spec | +| Idle draw | ~30W | ~40-45W | T2 Bench | +| AI inference (LLM) | 60-90W | 60-90W | T2 Bench | +| CPU-only load | 120-140W | 120-130W | T2 Bench | +| CPU + GPU load | ~200W | ~200W | T2 Bench | + +## 6. Environmental Bounds + +| Parameter | Dell (T0 Owner's Manual) | DGX Spark (T0 User Guide) | +|------------------------|------------------------------------|---------------------------------| +| Operating temperature | 0°C to 35°C (32°F to 95°F) | 5°C to 30°C (41°F to 86°F) | +| Storage temperature | -40°C to 65°C | — | +| Operating humidity | 10% to 90% (non-condensing) | 10% to 90% (non-condensing) | +| Operating altitude | -15.2 m to 3,048 m | Up to 3,000 m | +| Operating vibration | 0.66 GRMS | — | +| Operating shock | 110 G (2ms half-sine) | — | +| Noise | < 40 dB at 1-1.5m (T2 Bench) | — | + +## 7. Physical Bounds | Parameter | Value | |---------------|---------------| @@ -104,7 +130,7 @@ Rule of thumb: budget **1.2-1.5x** the raw model weight size for total inference | Footprint | 150 × 150 mm | | Height | 51 mm | -## 7. Validation Rules +## 8. Validation Rules When checking calculations: - Model size estimates should not exceed 128 GB (single) or 256 GB (stacked) diff --git a/context/gb10-superchip.md b/context/gb10-superchip.md index dbfa281..a910532 100644 --- a/context/gb10-superchip.md +++ b/context/gb10-superchip.md @@ -2,10 +2,10 @@ id: gb10-superchip title: "NVIDIA GB10 Grace Blackwell Superchip" status: established -source_sections: "Web research: NVIDIA newsroom, WCCFTech, Phoronix, The Register, Arm" +source_sections: "Web research: NVIDIA newsroom, WCCFTech, Phoronix, The Register, Arm, NVIDIA DGX Spark User Guide, Jeff Geerling, ServeTheHome" related_topics: [memory-and-storage, ai-frameworks, ai-workloads, connectivity, physical-specs] key_equations: [flops-fp4, nvlink-c2c-bandwidth] -key_terms: [gb10, grace-blackwell, superchip, cortex-x925, cortex-a725, blackwell-gpu, tensor-core, cuda-core, nvlink-c2c, soc] +key_terms: [gb10, grace-blackwell, superchip, cortex-x925, cortex-a725, blackwell-gpu, tensor-core, cuda-core, nvlink-c2c, soc, rt-core, nvenc, nvdec] images: [] examples: [] open_questions: @@ -35,6 +35,7 @@ The Grace CPU portion contains **20 cores** in a big.LITTLE-style configuration: - **10x ARM Cortex-A725** — efficiency cores Architecture: ARMv9.2 +**Processor cache:** 16 MB (T0 Spec, Dell Owner's Manual) This is the same Grace CPU lineage used in NVIDIA's data center Grace Hopper and Grace Blackwell products, adapted for desktop power envelopes. @@ -44,10 +45,17 @@ The Blackwell GPU portion features: - **6,144 CUDA cores** (comparable to the RTX 5070 core count) - **5th-generation Tensor Cores** — optimized for AI inference and training -- Peak performance: **1 PFLOP (1,000 TFLOPS) at FP4 precision** +- **4th-generation RT Cores** — ray tracing acceleration (T0 Spec) +- **1x NVENC / 1x NVDEC** — hardware video encode/decode engines (T0 Spec) +- **2 copy engines** (T0 Spec) +- Peak performance: **1 PFLOP (1,000 TFLOPS) at FP4 precision with sparsity** The Tensor Cores are the key differentiator for AI workloads, providing hardware acceleration for mixed-precision matrix operations used in deep learning. +### Measured FP64 Performance + +- **HPL (Linpack) FP64:** ~675 GFLOPS (T2 Benchmarked, Jeff Geerling) + ## 4. NVLink-C2C Interconnect The CPU and GPU communicate via NVLink Chip-to-Chip: @@ -60,8 +68,14 @@ This coherent memory architecture means there is no need to explicitly copy data ## 5. Power Envelope -- **System TDP:** ~140W (from related specifications) -- **External PSU:** 280W USB Type-C adapter (headroom for storage, networking, peripherals) +- **GPU TDP:** 140W (T0 Spec) +- **Idle power draw:** ~30W (T2 Benchmarked, Jeff Geerling) +- **CPU-only load:** ~120-140W (T2 Benchmarked, Jeff Geerling / ServeTheHome) +- **CPU + GPU load:** ~200W (T2 Benchmarked, ServeTheHome) +- **AI inference workloads:** 60-90W typical (T2 Benchmarked, ServeTheHome) +- **Dell external PSU:** 280W USB Type-C (vs. DGX Spark's 240W) + +The Dell Pro Max uses a higher-wattage PSU than the reference DGX Spark design, providing additional headroom for peripherals, QSFP optics, and storage. ## Key Relationships diff --git a/context/memory-and-storage.md b/context/memory-and-storage.md index c923e5a..a95b261 100644 --- a/context/memory-and-storage.md +++ b/context/memory-and-storage.md @@ -2,16 +2,15 @@ id: memory-and-storage title: "Memory and Storage" status: established -source_sections: "Web research: Dell product page, WCCFTech, Phoronix" +source_sections: "Web research: Dell product page, WCCFTech, Phoronix, NVIDIA DGX Spark User Guide, NVIDIA Developer Forums, Storage Review" related_topics: [gb10-superchip, ai-workloads, skus-and-pricing] key_equations: [memory-bandwidth, storage-throughput] -key_terms: [lpddr5x, unified-memory, nvme, pcie-gen4, sed] +key_terms: [lpddr5x, unified-memory, nvme, pcie-gen4, m2-2230, m2-2242, sed, opal] images: [] examples: [] open_questions: - - "Is the M.2 SSD user-replaceable or soldered?" - "Exact sequential and random IOPS for the included NVMe drives" - - "Memory channel configuration (number of channels)" + - "Which specific SSD model/brand is used in Dell vs. DGX Spark units" --- # Memory and Storage @@ -20,9 +19,10 @@ The Dell Pro Max GB10 features a unified memory architecture and NVMe solid-stat ## 1. System Memory -- **Capacity:** 128 GB LPDDR5X -- **Speed:** Up to 9,400 MT/s (megatransfers per second) -- **Bandwidth:** 273 GB/s +- **Capacity:** 128 GB LPDDR5X (T0 Spec) +- **Speed:** Up to 8,533 MHz / 9,400 MT/s (T0 Spec) +- **Bandwidth:** 273 GB/s (T0 Spec) +- **Interface:** 256-bit, 16 channels LPDDR5X (T0 Spec, NVIDIA DGX Spark User Guide) - **Architecture:** Unified coherent memory shared between CPU and GPU via [[gb10-superchip|NVLink-C2C]] ### Unified Memory Model @@ -33,13 +33,47 @@ Unlike traditional desktop systems with separate system RAM and GPU VRAM, the GB - AI models up to ~200B parameters can fit in memory (with quantization) - Frameworks see the full 128 GB as available device memory -The LPDDR5X is likely soldered to the SoC package (not user-upgradeable), consistent with the compact form factor. +The LPDDR5X is soldered to the SoC package and is **not user-upgradeable**. ## 2. Storage -- **Interface:** PCIe Gen 4 M.2 NVMe -- **Options:** 2 TB or 4 TB -- **SED-ready:** Self-Encrypting Drive support available on 4 TB option +- **Interface:** PCIe Gen 4 NVMe, up to 64 GT/s (T0 Spec, Dell Owner's Manual) +- **Form factors supported:** M.2 2230 **and** M.2 2242 (T0 Spec, Dell Owner's Manual) +- **User-replaceable:** Yes — the SSD is a **Field Replaceable Unit (FRU)** (T0 Spec, Dell Owner's Manual) + +### Available Drive Configurations (T0 Spec, Dell Owner's Manual) + +| Form Factor | Type | Interface | Capacity | Encryption | +|-------------|------|---------------------|------------|---------------------| +| M.2 2230 | TLC | PCIe Gen4 NVMe | 1 TB | No | +| M.2 2230 | QLC | PCIe Gen4 NVMe | 2 TB | No | +| M.2 2242 | TLC | PCIe Gen4 NVMe | 1 TB, 4 TB | Opal 2.0 SED | + +**CORRECTION:** Earlier research (NVIDIA Developer Forums) indicated PCIe Gen5 and 2242-only. The Dell Owner's Manual (Rev A01, Dec 2025) is authoritative: the interface is **PCIe Gen4** and **both 2230 and 2242** form factors are supported. + +### SSD Replacement Procedure (T0 Spec, Dell Owner's Manual) + +**Tools required:** Phillips screwdriver #0, T5 or T8 Torx screwdriver + +1. Shut down and disconnect power +2. Place computer top-side down on flat surface +3. Pry and lift the **rubber base plate** (magnetically attached, pry from left/right gaps) +4. Remove **4x M2x4.4 Torx screws** from the bottom cover +5. Use a plastic scribe to pry bottom cover, then gently flip it open + - **CAUTION:** Do not tension the antenna cables when handling the cover +6. Peel thermal pad from bottom cover (may be adhered to cover or SSD top) +7. Remove **1x M2x2 screw** securing the SSD to the system board +8. Slide and lift the SSD from its connector +9. Peel thermal pads from top and bottom of SSD + +**Installation** is the reverse. Adhere bottom thermal pad → top thermal pad → insert at angle → screw → close cover → 4 Torx screws → rubber base plate. + +### Screw Summary + +| Component | Screw Type | Quantity | +|---------------|------------|----------| +| Bottom cover | M2x4.4 Torx | 4 | +| SSD | M2x2 | 1 | Storage configurations map to SKU pricing — see [[skus-and-pricing]]. diff --git a/context/multi-unit-stacking.md b/context/multi-unit-stacking.md index d08cf2b..e6cb4ed 100644 --- a/context/multi-unit-stacking.md +++ b/context/multi-unit-stacking.md @@ -1,52 +1,108 @@ --- id: multi-unit-stacking title: "Multi-Unit Stacking" -status: provisional -source_sections: "Web research: WCCFTech, NVIDIA newsroom" +status: established +source_sections: "NVIDIA DGX Spark User Guide: Spark Stacking, Jeff Geerling review, ServeTheHome review" related_topics: [connectivity, gb10-superchip, ai-workloads, memory-and-storage] key_equations: [] -key_terms: [connectx-7, smartnic, qsfp, stacking, nvlink] +key_terms: [connectx-7, smartnic, qsfp, stacking, mpi, nccl, slurm, kubernetes] images: [] examples: [] open_questions: - - "Exact cable/interconnect required between units (QSFP type, length limits)" - - "Software configuration steps for multi-unit mode" - - "Performance overhead of inter-unit communication vs. single unit" - - "Does stacking appear as a single device to frameworks or require explicit multi-node code?" + - "Performance overhead of inter-unit communication vs. single unit (quantified)" - "Can more than 2 units be stacked?" + - "Actual tokens/sec for 405B models on stacked configuration" --- # Multi-Unit Stacking -Two Dell Pro Max GB10 units can be connected together to create a more powerful combined system, effectively doubling the available compute and memory. +Two Dell Pro Max GB10 units can be connected together to create a distributed compute cluster, effectively doubling the available compute and memory for running larger AI models. ## 1. How It Works -Each Dell Pro Max GB10 has **2x QSFP 200 Gbps ports** powered by the NVIDIA ConnectX-7 SmartNIC. These ports enable direct unit-to-unit connection: +Each Dell Pro Max GB10 has **2x QSFP56 200 Gbps ports** powered by the NVIDIA ConnectX-7 SmartNIC. These ports enable direct unit-to-unit connection: -- **Combined memory:** 256 GB unified (128 GB per unit) +- **Combined memory:** 256 GB (128 GB per unit, NOT unified — distributed across nodes) - **Combined compute:** 2 PFLOP FP4 (1 PFLOP per unit) -- **Interconnect bandwidth:** Up to 400 Gbps (2x 200 Gbps QSFP) +- **Interconnect:** 200GbE RDMA via QSFP56 DAC cable +- **CX-7 ports support Ethernet configuration only** — no InfiniBand (T1 Documented) -## 2. Model Capacity +## 2. Required Hardware + +### Approved QSFP DAC Cables (T1 Documented, NVIDIA DGX Spark User Guide) + +| Manufacturer | Part Number | Description | +|-------------|----------------------|------------------------------------------| +| Amphenol | NJAAKK-N911 | QSFP to QSFP112, 32AWG, 400mm, LSZH | +| Amphenol | NJAAKK0006 | 0.5m variant | +| Luxshare | LMTQF022-SD-R | QSFP112 400G DAC Cable, 400mm, 30AWG | + +These are short DAC (Direct Attach Copper) cables. The units are designed to sit directly on top of each other. + +## 3. Software Configuration (T1 Documented, NVIDIA DGX Spark User Guide) + +### Prerequisites +- Two DGX Spark / Dell Pro Max GB10 systems +- Both running Ubuntu 24.04 (or later) with NVIDIA drivers installed +- Internet connectivity for initial setup +- Root/sudo access on both systems + +### Network Setup + +**Option 1 — Automatic (Recommended):** +Use NVIDIA's netplan playbook downloaded from their repository. Applied via standard `netplan apply` commands. + +**Option 2 — Manual static IP:** +- Interface name: `enP2p1s0f1np1` +- Node 1: `192.168.100.10/24` +- Node 2: `192.168.100.11/24` +- Verify with ping test between nodes + +### SSH Configuration +The NVIDIA discovery script automates **passwordless SSH** between nodes, required for MPI communication. + +### Communication Frameworks +- **MPI** — inter-process CPU communication between nodes +- **NCCL v2.28.3** — GPU-accelerated collective operations across nodes + +### Verification +1. Ping connectivity test between nodes +2. Interface verification: `ip a` and `ethtool` +3. NCCL test suite execution (via NVIDIA playbook) + +## 4. How It Appears to Software + +Stacking does **NOT** present as a single logical device. It creates a **2-node distributed cluster** requiring explicit multi-node code: + +- Frameworks must use distributed execution (e.g., PyTorch Distributed, Megatron-LM) +- MPI handles inter-process communication +- NCCL handles GPU-to-GPU tensor transfers across the 200GbE link +- This is fundamentally different from a single larger GPU — there is communication overhead + +## 5. Model Capacity | Configuration | Memory | Max Model Size (approx) | |---------------|---------|-------------------------| | Single unit | 128 GB | ~200B parameters (FP4) | -| Dual stacked | 256 GB | ~400B parameters (FP4) | +| Dual stacked | 256 GB | ~405B parameters (FP4) | This enables running models like **Llama 3.1 405B** (with quantization) that would not fit in a single unit's memory. -## 3. Physical Configuration +## 6. Scaling Beyond 2 Units + +The documentation mentions potential for: +- **Job orchestration with Slurm or Kubernetes** +- **Containerized execution with Singularity or Docker** -The compact form factor (150x150x51mm per unit) is designed to be **stackable** — two units can sit on top of each other on a desk, connected via short QSFP cables. +Whether >2 units can be practically clustered is not explicitly documented, but the 200GbE RDMA networking and Slurm/K8s support suggest it is architecturally possible. -## 4. Open Areas +## 7. Physical Configuration -This feature is one of the less-documented aspects of the system. Key unknowns include the exact software configuration, whether it presents as a single logical device, and inter-node communication overhead. See open questions in frontmatter. +The compact form factor (150x150x51mm per unit) is designed to be **stackable** — two units sit on top of each other on a desk, connected via short (400-500mm) QSFP DAC cables. ## Key Relationships -- Connected via: [[connectivity]] (QSFP/ConnectX-7 ports) +- Connected via: [[connectivity]] (QSFP56/ConnectX-7 ports) - Extends capacity of: [[ai-workloads]] - Doubles resources from: [[gb10-superchip]], [[memory-and-storage]] +- Software stack: [[dgx-os-software]] diff --git a/context/open-questions.md b/context/open-questions.md index 84567ca..6f446a9 100644 --- a/context/open-questions.md +++ b/context/open-questions.md @@ -17,50 +17,40 @@ Catalog of known unknowns, research gaps, and unresolved questions about the Del - *Status:* Unknown. No official boost/base clocks published. - *Would resolve:* Performance prediction, thermal modeling - **Q:** What is the detailed per-precision TFLOPS breakdown (FP4/FP8/FP16/FP32/FP64)? - - *Status:* Only FP4 (1,000 TFLOPS) is officially published. Others are inferred. + - *Status:* FP4 = 1,000 TFLOPS (official). FP64 HPL = ~675 GFLOPS (benchmarked). Others inferred. - *Would resolve:* Accurate workload performance estimation -- **Q:** What is the thermal throttling behavior? - - *Status:* Unknown. Sustained vs. peak performance delta not documented. - - *Would resolve:* Real-world performance expectations ### Memory - **Q:** Is the LPDDR5X soldered or socketed? - - *Status:* Almost certainly soldered (given LPDDR5X and form factor), but not confirmed. - - *Would resolve:* Upgradeability -- **Q:** What is the memory channel configuration? - - *Status:* Unknown. Number of channels not published. - - *Would resolve:* Memory performance modeling + - *Status:* **Resolved** — see Resolved Questions below. ### Storage -- **Q:** Is the M.2 SSD user-replaceable? - - *Status:* Unknown. Owner's manual may clarify. - - *Would resolve:* Storage upgrade path +- **Q:** Which specific SSD model/brand is used in Dell vs. DGX Spark units? + - *Status:* Unknown. Only form factor (M.2 2242 PCIe Gen5) confirmed. + - *Would resolve:* Drive performance expectations, replacement sourcing - **Q:** What are the exact sequential and random IOPS? - - *Status:* Unknown. Drive model not publicly identified. + - *Status:* Unknown. No benchmarks published. - *Would resolve:* Storage performance expectations ## Software ### DGX OS - **Q:** Can stock Ubuntu 24.04 ARM be installed instead of DGX OS? - - *Status:* Likely possible but unsupported. Not documented. + - *Status:* Likely possible but unsupported. Not documented. Requires NVIDIA kernel. - *Would resolve:* OS flexibility -- **Q:** Full list of pre-installed NVIDIA packages and versions? - - *Status:* Partially known. Full manifest not published. +- **Q:** Full list of pre-installed NVIDIA packages and exact versions? + - *Status:* Major components known (CUDA, cuDNN, Docker, NGC, AI Enterprise, DGX Dashboard). Exact versions not published. - *Would resolve:* Development environment baseline -- **Q:** Does DGX OS include Docker/container runtime by default? - - *Status:* Unknown. - - *Would resolve:* Container workflow setup -- **Q:** OTA update mechanism and cadence? - - *Status:* Unknown. - - *Would resolve:* Maintenance planning +- **Q:** Update cadence and EOL timeline details? + - *Status:* 2-year guarantee mentioned (Jeff Geerling). Exact cadence unknown. + - *Would resolve:* Long-term maintenance planning ### AI Frameworks - **Q:** TensorFlow support status on ARM GB10? - *Status:* Unknown. Official vs. community builds unclear. - *Would resolve:* Framework selection for TF users - **Q:** Full NGC catalog availability for GB10? - - *Status:* Unknown. Which containers have ARM builds. + - *Status:* Unknown. Which containers have ARM64 builds. - *Would resolve:* Software ecosystem breadth - **Q:** vLLM or other inference server support on ARM Blackwell? - *Status:* Unknown. @@ -71,42 +61,30 @@ Catalog of known unknowns, research gaps, and unresolved questions about the Del ## Networking / Multi-Unit -- **Q:** What cable/interconnect is required for multi-unit stacking? - - *Status:* QSFP cables, but exact type/spec not documented. - - *Would resolve:* Multi-unit setup purchasing -- **Q:** Software configuration steps for multi-unit mode? - - *Status:* Not documented publicly. - - *Would resolve:* Multi-unit deployment -- **Q:** Does stacking appear as a single logical device to frameworks? - - *Status:* Unknown. May require explicit multi-node code. - - *Would resolve:* Development complexity for stacked setups - **Q:** Can more than 2 units be stacked? - - *Status:* Only 2-unit configuration documented. + - *Status:* Only 2-unit documented. Slurm/K8s support suggests possible. Not confirmed. - *Would resolve:* Maximum scaling potential -- **Q:** Can QSFP ports be used for general networking? - - *Status:* Unknown. May be reserved for stacking. - - *Would resolve:* Network architecture options +- **Q:** Performance overhead of inter-unit communication (quantified)? + - *Status:* 200GbE RDMA link, but no latency/overhead benchmarks published. + - *Would resolve:* Stacked vs. single performance expectations +- **Q:** Actual tokens/sec for 405B models on stacked config? + - *Status:* Unknown. + - *Would resolve:* Real-world stacking value proposition ## Physical / Environmental -- **Q:** Noise levels under load? - - *Status:* No dB measurements published. - - *Would resolve:* Office/desk suitability -- **Q:** Operating temperature range? - - *Status:* Unknown. - - *Would resolve:* Deployment environment requirements - **Q:** VESA mount compatibility? - *Status:* Unknown. - *Would resolve:* Mounting options -- **Q:** Cooling solution details (fan count, heatsink type)? - - *Status:* Unknown. - - *Would resolve:* Thermal management understanding +- **Q:** Exact heatsink dimensions and material? + - *Status:* Dual-fan + dense heatsink confirmed, but exact specs unknown. + - *Would resolve:* Aftermarket cooling or case modding potential ## Performance Benchmarks -- **Q:** Actual tokens/sec for common LLMs (Llama 3.3 70B, Mixtral, etc.)? - - *Status:* No published benchmarks from Dell or independent reviewers yet. - - *Would resolve:* Real-world inference performance expectations +- **Q:** Tokens/sec for Llama 3.3 70B specifically? + - *Status:* Only Llama 3.2 3B (~100 tok/s) and GPT-OSS-120B (~14.5 tok/s) benchmarked. + - *Would resolve:* Most common use case performance - **Q:** Fine-tuning time estimates for common model sizes? - *Status:* Unknown. - *Would resolve:* Training workflow planning @@ -118,8 +96,37 @@ Catalog of known unknowns, research gaps, and unresolved questions about the Del ## Resolved Questions -*(Move questions here as they get answered, with date and resolution)* - -| Date | Question | Resolution | Source | -|------|----------|------------|--------| -| — | — | — | — | +| Date | Question | Resolution | Source | +|------------|---------------------------------------------|-----------------------------------------------------------------|---------------------------------| +| 2026-02-14 | Is the M.2 SSD user-replaceable? | Yes — FRU. 4 Torx screws + 1 M2x2. Supports M.2 2230 AND 2242. PCIe Gen4. | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Memory channel configuration? | 256-bit interface, 16 channels LPDDR5X 8533 | NVIDIA DGX Spark User Guide | +| 2026-02-14 | Does DGX OS include Docker? | Yes — Docker + NVIDIA Container Runtime pre-installed | NVIDIA DGX Spark User Guide | +| 2026-02-14 | Operating temperature range? | Dell: 0-35°C; NVIDIA: 5-30°C | Dell Owner's Manual + NVIDIA UG | +| 2026-02-14 | Humidity range? | 10-90% non-condensing | NVIDIA DGX Spark User Guide | +| 2026-02-14 | Operating altitude? | Up to 3,000m (9,843 ft) | NVIDIA DGX Spark User Guide | +| 2026-02-14 | Noise levels under load? | Never exceeded 40 dB at 1-1.5m (non-stress) | ServeTheHome | +| 2026-02-14 | Cooling solution? | Dual-fan + dense heatsink, front-to-back airflow | Jeff Geerling, ServeTheHome | +| 2026-02-14 | BIOS/firmware update procedure? | apt upgrade + fwupdmgr, or DGX Dashboard GUI | ServeTheHome | +| 2026-02-14 | Network boot (PXE)? | Supported via UEFI → Advanced → Network Stack Configuration | NVIDIA DGX Spark User Guide | +| 2026-02-14 | First-boot wizard steps? | 10-step wizard documented (language, account, network, etc.) | NVIDIA DGX Spark User Guide | +| 2026-02-14 | QSFP cables for stacking? | Amphenol NJAAKK-N911/0006 or Luxshare LMTQF022-SD-R | NVIDIA DGX Spark User Guide | +| 2026-02-14 | Software config for stacking? | Netplan + SSH + MPI + NCCL v2.28.3 | NVIDIA DGX Spark User Guide | +| 2026-02-14 | Does stacking appear as single device? | No — 2-node distributed cluster, requires multi-node code | NVIDIA DGX Spark User Guide | +| 2026-02-14 | Can QSFP ports be used for general networking? | Yes — Ethernet config, 200GbE RDMA capable | Jeff Geerling | +| 2026-02-14 | Tokens/sec for common LLMs? | Llama 3.2 3B: ~100 tok/s; GPT-OSS-120B: ~14.5 tok/s | Jeff Geerling, ServeTheHome | +| 2026-02-14 | Thermal throttling behavior (Dell)? | Dell design prevents throttling; quieter than DGX Spark | Jeff Geerling | +| 2026-02-14 | Is LPDDR5X soldered? | Yes — soldered, not upgradeable | Form factor / LPDDR5X standard | +| 2026-02-14 | OTA update mechanism? | apt + fwupdmgr (CLI) or DGX Dashboard (GUI) | ServeTheHome | +| 2026-02-14 | HDMI version on Dell? | HDMI 2.1a (not 2.1b). Max 8K@30. | Dell Owner's Manual Rev A01 | +| 2026-02-14 | SSD interface speed? | PCIe Gen4 NVMe up to 64 GT/s (NOT Gen5 as forums suggested) | Dell Owner's Manual Rev A01 | +| 2026-02-14 | SSD form factors supported? | Both M.2 2230 and M.2 2242 | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Max display resolution? | USB-C DP: 8K@60; HDMI: 8K@30 | Dell Owner's Manual Rev A01 | +| 2026-02-14 | BIOS entry method? | Delete key for BIOS; F7 for one-time boot | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Full BIOS menu structure? | Main/Advanced/Security/Boot/Save&Exit fully documented | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Wireless module model? | AzureWave AW-EM637, 2.4/5/6 GHz, Wi-Fi 7, BT 5.4 | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Network controller model? | Realtek RTL8127-CG (10GbE) + NVIDIA ConnectX-7 (QSFP) | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Processor cache? | 16 MB | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Weight range? | 1.22-1.34 kg depending on configuration | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Power adapter dimensions? | 23 x 78 x 162 mm, multi-voltage output (5V-48V) | Dell Owner's Manual Rev A01 | +| 2026-02-14 | USB-C MST support? | Not supported (single display per port only) | Dell Owner's Manual Rev A01 | +| 2026-02-14 | Service tools required? | Phillips #0, T5 or T8 Torx screwdriver | Dell Owner's Manual Rev A01 | diff --git a/context/physical-specs.md b/context/physical-specs.md index e2ae708..a463679 100644 --- a/context/physical-specs.md +++ b/context/physical-specs.md @@ -2,17 +2,15 @@ id: physical-specs title: "Physical Specifications" status: established -source_sections: "Web research: Dell product page, WCCFTech" +source_sections: "Web research: Dell product page, WCCFTech, NVIDIA DGX Spark User Guide, Jeff Geerling, ServeTheHome" related_topics: [connectivity, gb10-superchip, skus-and-pricing] key_equations: [volume-calculation] key_terms: [form-factor, micro-desktop, usb-c-psu, tdp] images: [] examples: [] open_questions: - - "Noise levels under load (dB)" - - "Operating temperature range" - "VESA mount compatibility" - - "Cooling solution details (fan count, heatsink type)" + - "Exact heatsink dimensions and material" --- # Physical Specifications @@ -21,36 +19,103 @@ The Dell Pro Max GB10 is an ultra-compact mini desktop designed to sit on or nea ## 1. Dimensions and Weight -| Spec | Value | -|---------------|----------------------------| -| Width | 150 mm (5.9 in) | -| Depth | 150 mm (5.9 in) | -| Height | 51 mm (2.0 in) | -| Volume | ~1.15 liters | -| Weight | 1.31 kg (2.89 lbs) base | +| Spec | Dell Pro Max GB10 | DGX Spark (reference) | +|---------------|----------------------------|----------------------------| +| Width | 150 mm (5.9 in) | 150 mm | +| Depth | 150 mm (5.9 in) | 150 mm | +| Height (peak) | 51 mm (2.0 in) | 50.5 mm | +| Height (front/rear) | 45.5 mm (1.8 in) | — | +| Volume | ~1.15 liters | ~1.14 liters | +| Weight (min) | 1.22 kg (2.69 lbs) | 1.2 kg (2.6 lbs) | +| Weight (max) | 1.34 kg (2.96 lbs) | — | + +**Regulatory model:** D21U / D21U001 (Dell) For reference, the footprint is roughly the size of a large coaster or small book. ## 2. Power Supply -- **External adapter:** 280W USB Type-C -- **Connection:** USB-C power delivery -- **System TDP:** ~140W +| Parameter | Dell Pro Max GB10 | DGX Spark | +|-----------------|-------------------|---------------| +| PSU wattage | 280W | 240W | +| Connection | USB-C PD | USB-C PD | +| GPU TDP | 140W | 140W | + +The Dell PSU is 40W higher than the reference DGX Spark, providing extra headroom for QSFP optics and peripherals. + +### Dell 280W Power Adapter Details (T0 Spec, Dell Owner's Manual) + +| Parameter | Value | +|--------------------|----------------------------------------------| +| Dimensions | 23 x 78 x 162 mm (0.91 x 3.07 x 6.38 in) | +| Input voltage | 100-240 VAC (also 200-240 VAC) | +| Input frequency | 50-60 Hz | +| Input current (max)| 2A / 4A | +| Output voltages | 48V, 36V, 28V, 20V, 15V, 9V, 5V | +| Max output | 48V/5.83A, 36V/5.83A, 28V/5.89A, 20V/6.50A | + +### Power Button + +Located on the rear panel. Press to turn on. **Press and hold 4 seconds** to force shut down. (T0 Spec, Dell Owner's Manual) + +### Power Draw by Workload (T2 Benchmarked) + +| State | Power Draw | Source | +|--------------------|-------------|-----------------| +| Idle | ~30W | Jeff Geerling | +| AI inference (LLM) | 60-90W | ServeTheHome | +| CPU-only load | 120-140W | Jeff Geerling / STH | +| CPU + GPU load | ~200W | ServeTheHome | + +## 3. Cooling + +- **Design:** Dual-fan setup with dense heatsink (T2, reviews) +- **Airflow:** Front-to-back (Dell design is less restricted than DGX Spark) +- **Noise:** Never exceeded 40 dB at 1-1.5m during non-stress testing (T2, ServeTheHome) +- **Dell advantage:** Quieter than reference DGX Spark design; capable of keeping GB10 from thermal throttling (T2, Jeff Geerling) +- **Front panel:** Hard foam-like material allowing airflow intake +- **Bottom panel:** Large vent with rubber pad for desk stability; magnetically attached, reveals Wi-Fi antenna and system information underneath + +## 4. Environmental Specifications + +Dell and NVIDIA specs differ slightly. Dell's are from the Owner's Manual (T0 Spec); NVIDIA's from the DGX Spark User Guide. + +| Parameter | Dell Pro Max (T0) | DGX Spark (T0) | +|------------------------|------------------------------------|---------------------------------| +| Operating temperature | 0°C to 35°C (32°F to 95°F) | 5°C to 30°C (41°F to 86°F) | +| Storage temperature | -40°C to 65°C (-40°F to 149°F) | — | +| Operating humidity | 10% to 90% (non-condensing) | 10% to 90% (non-condensing) | +| Storage humidity | 0% to 95% (non-condensing) | — | +| Operating altitude | -15.2 m to 3,048 m (-50 to 10,000 ft) | Up to 3,000 m (9,843 ft) | +| Storage altitude | -15.2 m to 10,668 m (-50 to 35,000 ft) | — | +| Operating vibration | 0.66 GRMS | — | +| Storage vibration | 1.30 GRMS | — | +| Operating shock | 110 G (2ms half-sine) | — | +| Storage shock | 160 G (2ms half-sine) | — | +| Airborne contaminants | G1 per ISA-S71.04-1985 | — | + +**Note:** Dell's operating temp range (0-35°C) is wider than NVIDIA's (5-30°C). The Dell spec may reflect the Dell chassis thermal design improvements. + +### Power Adapter Environmental -The PSU is external, keeping the unit itself compact and cool. The 280W rating provides headroom beyond the ~140W system TDP for peripherals, storage, and networking. +| Parameter | Value | +|------------------------|------------------------------------| +| Operating temperature | 0°C to 35°C (32°F to 95°F) | +| Storage temperature | -40°C to 70°C (-40°F to 158°F) | -## 3. Form Factor +## 5. Form Factor -- **Classification:** Micro desktop / Mini PC +- **Classification:** Micro desktop / Mini PC / SFF (Small Form Factor) - **Design:** Stackable (for [[multi-unit-stacking]]) -- **Chassis:** Compact rectangular enclosure +- **Chassis:** Compact rectangular enclosure (gold-colored metal on DGX Spark) +- **Portability:** Fits in carry-on luggage or backpack (T2, ServeTheHome) -## 4. Scale Comparison +## 6. Scale Comparison | Compared to... | Dell Pro Max GB10 | |-------------------------|----------------------------| | Mac Mini M4 Pro | Similar footprint, thinner | -| NVIDIA DGX Spark | Identical hardware | +| NVIDIA DGX Spark | Same SoC, lighter, smaller PSU | | Traditional desktop | ~20x smaller by volume | | Laptop | Comparable weight | diff --git a/context/setup-and-config.md b/context/setup-and-config.md index 22e6643..cf0ac8c 100644 --- a/context/setup-and-config.md +++ b/context/setup-and-config.md @@ -1,17 +1,14 @@ --- id: setup-and-config title: "Setup and Configuration" -status: provisional -source_sections: "Web research: NVIDIA DGX OS 7 User Guide, Dell support KB" +status: established +source_sections: "Web research: NVIDIA DGX OS 7 User Guide, Dell support KB, NVIDIA DGX Spark User Guide, ServeTheHome" related_topics: [dgx-os-software, connectivity, physical-specs] key_equations: [] -key_terms: [first-boot, setup-wizard, grub, reinstall, dgx-os] +key_terms: [first-boot, setup-wizard, grub, reinstall, dgx-os, uefi, secure-boot, pxe] images: [] examples: [] open_questions: - - "Full first-boot wizard steps with screenshots" - - "BIOS/firmware update procedure" - - "Network boot (PXE) capabilities" - "Remote management / BMC / IPMI availability" - "Factory reset procedure beyond OS reinstall" --- @@ -22,22 +19,38 @@ Guide for initial setup, configuration, and recovery of the Dell Pro Max GB10. ## 1. Initial Setup (First Boot) +### Important: Device Powers On Immediately + +**The system starts up immediately when power is applied** — there is no separate power button press needed on first connection. Connect all peripherals before plugging in power. + ### Physical Setup 1. Place the unit on a stable surface (stackable design allows multiple units) -2. Connect the **280W USB-C power adapter** to the designated power USB-C port -3. Connect a display via **HDMI 2.1b** or **USB-C DisplayPort Alt Mode** -4. Connect keyboard and mouse (USB-C or Bluetooth) -5. Optionally connect **10GbE Ethernet** for wired networking +2. Connect a display via **HDMI** or **USB-C DisplayPort Alt Mode** + - If USB-C/DP shows no display, try HDMI instead (known compatibility issue) +3. Connect keyboard and mouse (USB-C or Bluetooth) +4. Optionally connect **10GbE Ethernet** for wired networking (recommended for faster setup) +5. Connect the **280W USB-C power adapter** (Dell) — system boots immediately + +### Access Methods + +**Local setup:** Connect keyboard, mouse, and display directly. Follow on-screen wizard. + +**Network setup:** The device creates a Wi-Fi hotspot on first boot. Credentials are on the Quick Start Guide sticker. Connect from another computer's web browser to configure remotely. + +### First Boot Wizard (T1 Documented, NVIDIA DGX Spark User Guide) -### First Boot Wizard -On first power-on, DGX OS presents a setup wizard: -1. Language and locale selection -2. User account creation -3. Network configuration (Wi-Fi 7 or Ethernet) -4. System preferences -5. Software configuration +1. **Language and time zone** selection +2. **Keyboard layout** (local setup only) +3. **Terms and conditions** acceptance +4. **User account creation** (username and password) +5. **Information sharing settings** (optional analytics/crash reporting) +6. **Wi-Fi network selection** (skipped if Ethernet connected) +7. **Wi-Fi password** entry +8. **Network connection** to home network +9. **Software download and installation** (up to 10 minutes; system may reboot multiple times) +10. **Automatic reboot** upon completion -The wizard is designed for fast onboarding — the system is ready to use shortly after. +**WARNING:** Do not shut down or reboot during the software update step. The installation cannot be interrupted once the download begins — powering down during updates can cause system damage. ## 2. OS Reinstallation @@ -55,26 +68,116 @@ Source: [Dell Support — How to Reinstall DGX OS](https://www.dell.com/support/ ## 3. Post-Setup Configuration ### Recommended Steps -- Update DGX OS packages: `sudo apt update && sudo apt upgrade` +- Update all packages and firmware: + ```bash + sudo apt update && sudo apt upgrade + sudo fwupdmgr refresh && sudo fwupdmgr upgrade + ``` - Verify GPU is detected: `nvidia-smi` - Verify CUDA toolkit: `nvcc --version` - Configure SSH for remote access -- Set up development environment (Jupyter, conda/venv, etc.) +- Access DGX Dashboard (web UI with integrated JupyterLab) +- Browse tutorials at https://build.nvidia.com/spark ### Network Configuration - **Wi-Fi 7:** Configure via Network Manager or `nmcli` - **10GbE Ethernet:** Auto-configured via DHCP or manual static IP - **QSFP ports:** For [[multi-unit-stacking]] configuration -## 4. Troubleshooting +### Access Methods (Post-Setup) +- **Local:** Keyboard, mouse, monitor directly connected +- **SSH:** Standard SSH remote access +- **NVIDIA Sync:** Remote management application +- **Remote desktop:** Supported +- **Hybrid:** Local + network access simultaneously + +## 4. UEFI/BIOS Settings (T0 Spec, Dell Owner's Manual + NVIDIA DGX Spark User Guide) + +### Entering BIOS + +- **BIOS Setup:** Restart and press **Delete** key at Dell logo (T0 Spec, Dell Owner's Manual) +- **One-time boot menu:** Restart and press **F7** at Dell logo (T0 Spec, Dell Owner's Manual) + +### Navigation Keys + +| Key | Action | +|------------|---------------------------| +| Up/Down | Move between fields | +| Left/Right | Move between menus | +| Enter | Select value / follow link| +| F1 | General help | +| F2 | Restore previous values | +| F3 | Apply optimized defaults | +| F4 | Save and exit | +| ESC | Exit without saving | + +### BIOS Menu Structure (T0 Spec, Dell Owner's Manual) + +**Main:** BIOS info, system language, date/time + +**Advanced:** +- Trusted Computing (Security Device Support) +- Serial Port Console Redirection (COM0) +- Network Stack Configuration (IPv4/IPv6 PXE, HTTP boot, PXE wait time) +- NVMe Configuration (model, size, device self-test) +- TLS Auth Configuration (Server CA, Client Cert) +- Platform Configuration: **iGPU Memory Carveout**, **DRAM Encryption**, DRAM Voltage Level, Watchdog Timer +- VLAN Configuration +- MAC IPv4/IPv6 Network Configuration (DHCP, static IP) + +**Security:** +- Administrator and User passwords (policy: 1 lower, 1 upper, 1 number, 1 special char) +- Media Sanitization +- Secure Boot (default: Enabled; supports Expert Key Management, Factory Keys) +- TCG Storage Security (Opal SED management) + +**Boot:** +- Boot Option Priorities, Fast Boot, Quiet Boot +- Add/Delete Boot Options +- Bootup Numlock State + +**Save & Exit:** +- Save/discard changes, restore defaults, boot override + +### Key Settings Quick Reference + +| Setting | Location | Notes | +|---------------------------|---------------------------------------------|--------------------------------| +| Wi-Fi & Bluetooth | Advanced → IO Port Access | Enable/disable together | +| Boot order | Boot → Boot Option Priorities | Configure boot device order | +| One-time USB boot | Press F7 at Dell logo, or Save & Exit menu | Temporary boot override | +| Secure Boot | Security → Secure Boot | Default: Enabled | +| Network Stack (PXE) | Advanced → Network Stack Configuration | IPv4/IPv6 PXE/HTTP support | +| iGPU Memory Carveout | Advanced → Platform Configuration | GPU memory allocation | +| DRAM Encryption | Advanced → Platform Configuration | Memory encryption toggle | +| NVMe Self-Test | Advanced → NVMe Configuration | Short and extended self-test | +| Media Sanitization | Security → Media Sanitization | Secure drive wipe | +| Clear passwords | Contact Dell technical support | Cannot be done in BIOS alone | + +## 5. Troubleshooting | Symptom | Check | |-----------------------------|----------------------------------------------| -| No display output | Try both HDMI and USB-C DP Alt Mode | +| No display on USB-C | Try HDMI instead (known DP Alt Mode issue) | +| No display at all | Try both HDMI and USB-C DP Alt Mode | | GPU not detected | Run `nvidia-smi`, check driver installation | -| Network not connecting | Verify cable/Wi-Fi config, run `ip addr` | -| System won't boot | Access GRUB menu, try OS reinstall | +| Network not connecting | Network power cycle (see below) | +| System won't boot | Access GRUB menu (Delete key), try OS reinstall | | Slow AI performance | Check `nvidia-smi` for thermal throttling | +| Firmware update needed | Run `sudo fwupdmgr refresh && upgrade` | +| Force shutdown needed | Press and hold power button 4 seconds | +| NVMe health check | BIOS → Advanced → NVMe Configuration → Self Test | + +### Network Power Cycle (T0 Spec, Dell Owner's Manual) + +If unable to access the Internet: +1. Turn off the computer +2. Turn off the modem +3. Turn off the wireless router +4. Wait 30 seconds +5. Turn on the wireless router +6. Turn on the modem +7. Turn on the computer ## Key Relationships diff --git a/context/skus-and-pricing.md b/context/skus-and-pricing.md index a0f1665..cd0fc93 100644 --- a/context/skus-and-pricing.md +++ b/context/skus-and-pricing.md @@ -2,7 +2,7 @@ id: skus-and-pricing title: "SKUs and Pricing" status: established -source_sections: "Web research: Dell product page, WCCFTech, Phoronix" +source_sections: "Web research: Dell product page, WCCFTech, Phoronix, Dell Owner's Manual Rev A01" related_topics: [memory-and-storage, physical-specs] key_equations: [] key_terms: [fcm1253, sku] @@ -21,10 +21,14 @@ The Dell Pro Max GB10 is available in two primary storage configurations. ## 1. Available Models -| Model | Storage | SED | Price (USD) | -|-------------------|---------|------|-------------| -| FCM1253 (2TB) | 2 TB | No | $3,699 | -| FCM1253 (4TB) | 4 TB | Yes | $3,999 | +| Model | Storage | Form Factor | Type | SED | Price (USD) | +|-------------------|---------|-------------|------|------------|-------------| +| FCM1253 (2TB) | 2 TB | M.2 2230 | QLC | No | $3,699 | +| FCM1253 (4TB) | 4 TB | M.2 2242 | TLC | Opal 2.0 | $3,999 | + +Additional storage options per Dell Owner's Manual: +- **1 TB M.2 2230 TLC** — PCIe Gen4 NVMe (likely not a standard retail SKU) +- **1 TB M.2 2242 TLC SED** — PCIe Gen4 NVMe, Opal 2.0 Both models share identical compute and memory specifications: @@ -32,11 +36,13 @@ Both models share identical compute and memory specifications: - 128 GB LPDDR5X - All connectivity options -The only differentiator between SKUs is storage capacity and SED (Self-Encrypting Drive) support. +The primary differentiators between SKUs are storage capacity, form factor (2230 vs 2242), NAND type (QLC vs TLC), and SED support. ## 2. Model Number - **Dell model identifier:** Dell Pro Max FCM1253 +- **Regulatory model:** D21U +- **Regulatory type:** D21U001 - **Form factor designation:** Micro ## 3. Release Timeline diff --git a/phases/phase-02-deep-research.md b/phases/phase-02-deep-research.md new file mode 100644 index 0000000..765cc2d --- /dev/null +++ b/phases/phase-02-deep-research.md @@ -0,0 +1,77 @@ +# Phase 2: Deep Research — Reviews, Official Docs, Community Data + +**Date:** 2026-02-14 +**Goal:** Fill gaps from Phase 1 by integrating official NVIDIA documentation, independent reviews, and community findings + +## What Was Done + +1. Attempted to access Dell Owner's Manual PDF — blocked by 403 on Dell support site and manuals.plus +2. Found and ingested **NVIDIA DGX Spark User Guide** (HTML version at docs.nvidia.com) — the authoritative hardware/software reference +3. Ingested **Jeff Geerling's review** — power measurements, benchmarks, thermal analysis, networking throughput +4. Ingested **ServeTheHome review** — power draw by workload, noise levels, LLM benchmarks, port layout details +5. Ingested **Tom's Hardware review** — overall verdict, rating (4/5) +6. Ingested **NVIDIA Developer Forums** — SSD replacement details (M.2 2242 form factor confirmed) +7. Ingested **ServeTheHome firmware article** — Dell vs NVIDIA firmware signing, update procedures + +## Sources Added + +- NVIDIA DGX Spark User Guide: Hardware Overview (docs.nvidia.com/dgx/dgx-spark/hardware.html) +- NVIDIA DGX Spark User Guide: System Overview (docs.nvidia.com/dgx/dgx-spark/system-overview.html) +- NVIDIA DGX Spark User Guide: First Boot (docs.nvidia.com/dgx/dgx-spark/first-boot.html) +- NVIDIA DGX Spark User Guide: UEFI Settings (docs.nvidia.com/dgx/dgx-spark/uefi-settings.html) +- NVIDIA DGX Spark User Guide: Spark Stacking (docs.nvidia.com/dgx/dgx-spark/spark-clustering.html) +- NVIDIA DGX Spark User Guide: Software (docs.nvidia.com/dgx/dgx-spark/software.html) +- Jeff Geerling: "Dell's version of the DGX Spark fixes pain points" (jeffgeerling.com) +- ServeTheHome: "NVIDIA DGX Spark Review" (servethehome.com) — pages 1 and 4 +- ServeTheHome: "NVIDIA DGX Spark and Dell Partner GB10 Firmware" (servethehome.com) +- Tom's Hardware: "Nvidia DGX Spark review" (tomshardware.com) +- NVIDIA Developer Forums: "Exchange internal SSD" thread (forums.developer.nvidia.com) +- Storage Review teardown (referenced in forums) + +## Key Findings + +### Resolved 18 open questions: +- SSD is user-replaceable FRU (M.2 2242 PCIe Gen5) +- Memory: 256-bit, 16 channels +- Docker + NVIDIA Container Runtime pre-installed +- Environmental: 5-30°C, 10-90% humidity, up to 3,000m altitude +- Noise: < 40 dB at 1-1.5m +- Cooling: Dual-fan + dense heatsink, front-to-back airflow +- Firmware: apt + fwupdmgr (Dell uses different signed firmware from NVIDIA) +- PXE boot supported via UEFI +- First boot: 10-step wizard fully documented +- Stacking: Specific QSFP DAC cables documented, MPI + NCCL v2.28.3, ethernet-only +- Stacking is 2-node distributed cluster (NOT single logical device) +- QSFP ports usable for general 200GbE networking +- Benchmark data: Llama 3.2 3B ~100 tok/s, GPT-OSS-120B ~14.5 tok/s +- Dell design prevents thermal throttling (better than DGX Spark reference) +- Power draw profiled across all workload types +- HDMI display compatibility issue documented +- 2-year support guarantee +- Dell PSU is 280W vs DGX Spark 240W + +### New data added: +- RT Cores (4th gen), NVENC, NVDEC specs +- FP64 HPL benchmark: ~675 GFLOPS +- Gaming performance (Cyberpunk, Doom Eternal via FEX/Proton) +- USB ports are USB 3.2 Gen 2x2 +- QSFP connected via x4 PCIe Gen 5 +- Regulatory model: D21U / D21U001 +- DGX Spark weight (1.2kg) vs Dell (1.31kg) differentiated +- UEFI menu structure documented +- Software stack: NVIDIA Sync, DGX Dashboard, AI Enterprise, NGC confirmed +- Stacking cable part numbers (Amphenol, Luxshare) +- Stacking IP configuration (192.168.100.10/11) + +## What Changed + +All 12 context files updated. open-questions.md rebuilt with 18 resolved items. + +## Remaining Gaps + +- Dell Owner's Manual PDF still not ingested (403 from all sources — needs manual download) +- DGX Spark UEFI Manual (separate document, not yet found online) +- Exact TFLOPS for FP8/FP16/FP32 still inferred +- No Llama 3.3 70B specific tokens/sec benchmark +- No fine-tuning benchmarks +- No image generation benchmarks diff --git a/phases/phase-03-owners-manual.md b/phases/phase-03-owners-manual.md new file mode 100644 index 0000000..e2ba02c --- /dev/null +++ b/phases/phase-03-owners-manual.md @@ -0,0 +1,88 @@ +# Phase 3: Dell Owner's Manual Integration + +**Date:** 2026-02-14 +**Goal:** Parse the full Dell Pro Max GB10 FCM1253 Owner's Manual (Rev A01, Dec 2025, 45 pages) and integrate into knowledge base + +## Source + +- `reference/sources/dell-pro-max-with-gb10-fcm1253-om-en-us.pdf` +- Extracted via PyMuPDF (fitz), all 45 pages parsed successfully + +## Critical Corrections Made + +These findings from the authoritative Dell Owner's Manual contradict earlier data from web research and NVIDIA forums: + +1. **SSD is PCIe Gen4, NOT Gen5** — NVIDIA Developer Forums and Storage Review teardown claimed Gen5. Dell Owner's Manual (Rev A01, Dec 2025) says PCIe Gen4 NVMe, up to 64 GT/s. + +2. **Supports BOTH M.2 2230 AND M.2 2242** — Earlier research indicated 2242-only. Manual lists 2230 (1TB TLC, 2TB QLC) and 2242 (1TB/4TB TLC SED Opal 2.0). + +3. **HDMI is 2.1a, NOT 2.1b** — Initial web research from Dell product page suggested 2.1b. Manual confirms 2.1a (matching DGX Spark spec). + +4. **Operating temperature range is 0-35°C (Dell), not 5-30°C (NVIDIA)** — Dell's spec is wider. This may reflect Dell's improved thermal design. + +5. **Bottom cover screws are Torx (M2x4.4), not Phillips** — Earlier sources said Phillips. Manual specifies T5 or T8 Torx screwdriver required. + +6. **Weight range is 1.22-1.34 kg** — Not a single 1.31 kg figure. Varies by configuration. + +## New Data Added + +### Hardware Details +- Processor cache: 16 MB +- All ports are on the BACK (front has no ports) +- Power button: press to turn on, hold 4 seconds to force shutdown +- Service tag location: bottom of unit +- Rubber base plate: magnetically attached, pry from left/right gaps +- Bottom cover: 4x M2x4.4 Torx screws +- SSD: 1x M2x2 screw, thermal pads on top and bottom +- Required tools: Phillips #0, T5 or T8 Torx + +### Display Specifications +- USB-C DP 1.4a: max 7680x4320 at 60 Hz (8K@60) +- HDMI 2.1a: max 7680x4320 at 30 Hz (8K@30) +- MST (Multi-Stream Transport): Not supported +- Cable recommendation: connect right to left, ≤6.5mm width + +### Networking +- Realtek RTL8127-CG (10GbE Ethernet controller) +- AzureWave AW-EM637 Wi-Fi module (2.4/5/6 GHz) +- Encryption: 128-bit AES-CCMP, 256-bit AES-GCMP, 256-bit AES-GMAC + +### Power Adapter +- Dimensions: 23x78x162 mm +- Input: 100-240VAC, 50-60Hz +- Multi-voltage output: 48V/36V/28V/20V/15V/9V/5V + +### Environmental (Dell-specific) +- Operating: 0-35°C, 10-90% humidity, -15.2m to 3048m altitude +- Storage: -40 to 65°C, 0-95% humidity, -15.2m to 10668m altitude +- Vibration: 0.66 GRMS operating, 1.30 GRMS storage +- Shock: 110G operating, 160G storage (2ms half-sine) +- Airborne contaminants: G1 per ISA-S71.04-1985 + +### BIOS/UEFI (Full Structure) +- Entry: Delete key at Dell logo (BIOS), F7 (one-time boot) +- Navigation: F1=Help, F2=Restore, F3=Defaults, F4=Save&Exit, ESC=Exit +- Menus: Main, Advanced, Security, Boot, Save & Exit +- Advanced: Platform Configuration (iGPU Memory Carveout, DRAM Encryption, Watchdog Timer), Network Stack, NVMe Config with self-test, VLAN, TLS Auth +- Security: Secure Boot, Media Sanitization, TCG Storage (Opal), Expert Key Management, password policies +- Boot: Boot priorities, Fast Boot, Quiet Boot, custom boot options + +### SKU Details +- 2TB model uses M.2 2230 QLC (no SED) +- 4TB model uses M.2 2242 TLC with Opal 2.0 SED +- Additional 1TB options exist (2230 TLC and 2242 TLC SED) + +### Troubleshooting +- Network power cycle procedure (7 steps) +- Force shutdown: hold power 4 seconds +- NVMe self-test via BIOS + +## Files Updated + +All 12 context files updated. 14 additional resolved questions added to open-questions.md. + +## Remaining Gaps + +- Figures/diagrams from manual are referenced but not visually captured (PDF images) +- Full UEFI Manual (separate document referenced in Dell manual) not yet found +- DGX Spark-specific BIOS differences (if any) unknown diff --git a/reference/sources/dell-pro-max-with-gb10-fcm1253-om-en-us.pdf b/reference/sources/dell-pro-max-with-gb10-fcm1253-om-en-us.pdf new file mode 100644 index 0000000..c354b5c Binary files /dev/null and b/reference/sources/dell-pro-max-with-gb10-fcm1253-om-en-us.pdf differ