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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [LoRA][Perf] Zero-slice early-exit for LoRA kernels
- [DO NOT REVIEW][Kernel][Helion] Eager call-site routing for per_token_group_fp8_quant
- [ROCm] Enable AITER by default
- [Bugfix] Apply EP weight filter in multithreaded safetensors loader
- [Model Runner V2][Spec Decode] Add multi-layer MTP speculator
- [Bug]: EAGLE-3 + prompts >2048 tokens: device-side assert (Triton `index < 2048`) in inductor-compiled eagle_head kernels; eager works, cudagraph_mode=NONE still crashes (v0.24.0)
- [Bug]: moe_wna16_marlin_gemm applies wrong per-row topk weights (mul_topk_weights=True) at gpt-oss NVFP4 MoE shapes — corrupt output
- [Attention] Add direct symmetric-memory DCP A2A
- [BugFix] Prefer per-spec cache_dtype_str when reshaping KV cache
- [Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses
- Docs
- Python not yet supported