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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend][OpenAI] Forward thinking_token_budget to chat_template_kwargs in ChatCompletionRequest
- [Core] Bound EngineCore shutdown on fatal error to prevent wedged-worker hangs
- [Bugfix][SM120][MLA] Read fp8_ds_mla tile scales as arbitrary fp32
- [Tests][ROCm] Give AITER combos a 0/1 expert_mask in the modular-kernel sweep
- [Bugfix] return False from is_moe_layer when no MoE base matches
- [Frontend] Port the MuseGlimmer reasoning parser to the Streaming Parser Engine
- [Docs] Document NIXL KV connector metrics aggregation semantics
- [Core] Add XPress speculative decoding method
- [Bugfix][Model] Fix Nemotron GGUF LayerNorm and embedding handling
- [Bug]: sampler warmup misses the plain-greedy path — spec-decode rejection kernels JIT on the first request
- Docs
- Python not yet supported