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
- [Core] Add `max_num_queued_reqs` and `max_num_queued_tokens` for queue size management
- [Online quantization] Add online MXFP4 quantization support
- [Bugfix] Skip Qwen3 deepstack buffers without vision
- [ZenCPU] Minimal zen image build on x86 premerge queue
- [Bug]: Tools streaming internal error when `VLLM_ENFORCE_STRICT_TOOL_CALLING=false` and `tool_choice=required`
- [CI/Build][The Rock] Use model_class_overrides so spawned worker can use test PredictableLlamaForCausalLM class when worker spawned using Python 3.14
- [Bug]: Model Runner V2 (now default for dense models) skips CUDA graph memory reservation — `profile_cudagraph_memory()` returns 0, causing OOM during `capture_model()`
- [KV-offload][FS]: Batching for read/write threads
- [Bugfix][Structured Output] Mask request stop tokens in xgrammar until grammar terminates
- [RFC]: ReplaySSM: cache SSM inputs instead of state for faster standard and speculative decode (Mamba2 + GDN)
- Docs
- Python not yet supported