TokenSpeed, a 'speed-of-light' LLM inference engine for Blackwell and Rubin, hits 2.3k stars
lightseekorg · github · 2026-10-15
Trending GitHub repo lightseekorg/tokenspeed (Python, 2.3k stars) bills itself as a speed-of-light LLM inference engine, targeting NVIDIA Blackwell (B200/B300), GB200/GB300, Rubin and AMD MI355X/MI455X, with support for DeepSeek, GLM, Kimi, Qwen, MiniMax, GPT-OSS and VLMs. Details are sparse but the hardware and model coverage stand out.
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15