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
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][ROCm] AITER MLA: size MTP verification decode metadata for real qlen/dtype
- [V1][Spec Decode] Relaxed acceptance for thinking-phase tokens (port of #22238)
- [Backport][v0.19.1] Fix GLM5.1 Codex Responses API Bad Request
- fix: correct apply_chat_template signature in DeepseekV4Renderer (closes #44949)
- [Core][PD] Role-aware optimizations for Spec decoding
- [SD][PD] Skip speculator sampling on P in disaggregated
- [Bug]: VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS is enabled by default and overestimates memory requirements (lowering KV cache space)
- [Bug]: vllm hangs at Triton kernel JIT compilation during inference: _zero_kv_blocks_kernel with TP=2
- [Bug]: Hybrid-model prefix caching silently drops to 0% when the align-mode Mamba checkpoint lands in request-unique tokens
- [Bugfix] MoRIIO toy P/D proxy: add /health
- Docs
- Python not yet supported