Popular repositories Loading

1. glm53-flash-exl3-2x-dgx-spark glm53-flash-exl3-2x-dgx-spark Public

   GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spec decode

   Python 65 5

2. dgx-spark-2x-deepseek-v4-flash dgx-spark-2x-deepseek-v4-flash Public

   Reproducible kit to deploy DeepSeek-V4-Flash-DSpark on a 2× NVIDIA DGX Spark (GB10) cluster: vLLM TP=2 over QSFP 200GbE, NVFP4 KV, DSpark speculative decoding, 1M context, systemd self-heal. Apache…

   Python 13 3

3. grok-build-codex-plugin grok-build-codex-plugin Public

   Codex CLI plugin: delegate reviews and bounded coding tasks to the local Grok Build CLI via a bundled MCP server

   JavaScript 6 1

4. deepseek-v41-flash-reap-2x-dgx-spark deepseek-v41-flash-reap-2x-dgx-spark Public

   Serve DeepSeek-V4.1-Flash REAP-256E (native FP4) on 2x DGX Spark: 25.65 tok/s decode with DSpark speculative decoding, 64K context, reproducible receipts

   Python 2

5. glm53-flash-fp4-b12x-2x-dgx-spark glm53-flash-fp4-b12x-2x-dgx-spark Public

   Deployment kit: nvidia/GLM-5.3-Flash-FP4-Local on 2x DGX Spark with vLLM + FlashInfer b12x (TP2, MTP-5, 1M context, RoCEnante)

   Python 2

6. claude-code-cli-companions claude-code-cli-companions Public

   Forked from openai/codex-plugin-cc

   Claude Code CLI marketplace for Codex and Grok Build reviews, second opinions, and bounded delegated tasks.

   JavaScript 1