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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Installation]: [ROCm] Gemma4 multimodal model fails to start on vLLM 0.32.0 due to excessive video encoder memory reservation (negative KV cache)
- [Bug]: Qwen3.6 GDN greedy DFlash2 divergence from batch-dependent numerics and preemption/recompute (v0.31.0)
- [RL] Support partitioned trainer source groups for NCCL M2N
- [Bugfix][NIXL] Save chunked host-buffer prefills after their final chunk
- [Bugfix][Security] muse: fix quadratic attribute scans in tool-call extraction
- [CPU] Add AArch64 top-k and top-p sampling kernels
- [Bugfix][ROCm][MoRIIO] Slice WRITE heads by each layer's head count
- [XPU][KV Connector] Fix MooncakeStoreConnector on Intel XPU
- [Bug]: Responses API: tool_choice=allowed_tools does not work
- [Recipe] Align Kimi-K3 Ascend variants and Mooncake V2 PD
- Docs
- Python not yet supported