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 supported50 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][OpenAI] Suppress hidden reasoning metadata in batch responses
- [Bugfix] Fix malformed stale-tensor discard warning in TensorIpcReceiver
- [Bugfix][Frontend] Fix Responses item status and Harmony event lifecycle
- [Bug]: Engine-resolved prefix-cache match unit is not propagated to workers
- [Bugfix] Exclude SM107 (Rubin) from support_deep_gemm()
- FlashInfer autotune for trtllm_fp4_block_scale_moe wedges forever on SM103 (GB300): trtllm_gemm cubin is sm_100a-only, no PTX, and the autotuner has no timeout
- [Bug]: NixlConnector CPU core reservation ignores the cgroup cpuset, killing the worker in containers
- [Bugfix][NIXL] Don't fail a completed KV transfer when telemetry is unavailable
- Fix QSA metadata with graph-padded query offsets
- [Core][KVConnector] Drain receives and preserve retained KV during keep pauses
- Docs
- Python not yet supported