Reproducible refusal-subspace editing and TP=2 deployment of DeepSeek V4 Flash 0731 on two DGX Sparks
-
Updated
Aug 14, 2026 - Python
#
nvidia-gb10
Here are 10 public repositories matching this topic...
DeepSeek-V4-Flash + DSpark speculative decoding on a pair of NVIDIA DGX Sparks (vLLM TP=2 over RoCE) — tuned recipe, overlays that halve multi-turn TTFT, contamination-guarded benchmarks, ops runbook
-
Updated
Jul 3, 2026 - Python
Production-oriented Qwen3.6-35B-A3B-NVFP4-Fast vLLM deployment for NVIDIA DGX Spark / GB10
-
Updated
Jul 12, 2026 - Shell
Measured Muse Glimmer 30B recipe for NVIDIA DGX Spark, with llama.cpp, DFlash parity checks, vision, tools, and GB10 benchmarks.
-
Updated
Aug 10, 2026 - Python
Reproducible high-speed Qwen3.6-35B-A3B inference on NVIDIA GB10
-
Updated
Aug 7, 2026 - Python
Benchmark for GB10 - Nvidia DGX Spark
quantization model-evaluation huggingface inference-benchmark llama-cpp vllm gptq local-llm local-ai tool-calling agent-benchmark llm-benchmark nvfp4 nvidia-gb10 dgx-spar dgx-spark-benchmark nokast
-
Updated
Aug 16, 2026 - Python
Auditable DeepSeek V4 Flash inference evidence on two NVIDIA GB10 systems
-
Updated
Aug 6, 2026 - Python
Production-ready local AI agent stack for NVIDIA DGX Spark / ASUS GB10. Gemma 4 31B NVFP4 + bge-m3 embeddings + OpenClaw gateway, one docker compose up.
agent docker-compose self-hosted arm64 multimodal rag blackwell vllm local-llm bge-m3 tool-calling nvfp4 dgx-spark nvidia-dgx grace-blackwell openclaw nvidia-gb10 gemma-4 asus-gb10 gb10-superchip
-
Updated
Aug 3, 2026 - Python
Auditable DeepSeek V4 Flash inference evidence on two NVIDIA GB10 systems
-
Updated
Aug 10, 2026 - Python
Empirical NVIDIA GB10 and SM121 microarchitecture characterization
-
Updated
Aug 9, 2026 - Python
Improve this page
Add a description, image, and links to the nvidia-gb10 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nvidia-gb10 topic, visit your repo's landing page and select "manage topics."