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
- [Bug]: NIXL HMA receive failures can return HTTP 200 with corrupted tokens
- [Kernel] Fix vllm_c fused_add_rms_norm to match native IR rounding semantics
- [Bug]: EngineCore blocks forever (no timeout) in AsyncModelRunnerOutput copy_event. synchronize() when a GPU kernel never terminates
- [Bug]: Error while trying Speculative Decoding on Intel XPU for Qwen/Qwen3.6-35B-A3B
- [Bugfix][Parser] Preserve engine content without tool calls
- [Bug]: Synchronized FlashInfer autotune deadlocks multi-node TP startup on hosts without GPUDirect RDMA (GB10/DGX Spark)
- [MRv2][Bugfix] Sync speculative draft tokens across PP ranks
- [Bugfix] Validate guidance tokenizer compatibility before EngineCore
- [ROCm][Perf] Use Aiter's CA Output Variant for Kimi-K3
- [Bugfix] Unwrap multimodal target only when needed in DSpark
- Docs
- Python not yet supported