vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported31 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Opt-in fused shared-expert gate + GDN in-proj fusion + prefill scan-output copy elision for Qwen3.5-122B-A10B-NVFP4 (Blackwell SM103)
- [MoE] Plumb gemm1_alpha/beta/clamp_limit into TRT-LLM FP8 MoE
- [Core] Add soft thinking token budget with progressive logit bias
- [Ray] Default DP workers to mp-style device placement for symmetric memory
- [Core] Update PyTorch to 2.13.0, torchvision to 0.28.0, triton to 3.7.1 (test channel)
- [NVFP4] Support clamped SwiGLU-OAI (SwigluBias) on FlashInfer-CUTLASS MoE
- [Perf] Restore zero-init of swizzled NVFP4 scale buffer to recover Blackwell decode throughput
- [Perf]: Severe NVFP4 decode throughput regression on Blackwell (B300/GB300): uninitialized swizzled scale buffer in `create_fp4_scale_tensor`
- [Bug]: Responses API streaming for GPT-OSS Harmony crashes OpenAI SDK with `IndexError` due to incorrect `content_index` logic
- [Bugfix] Reset per-item content_index in gpt-oss Responses streaming
- Docs
- Python not yet supported