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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Model] Qwen3-ASR realtime: SDK-style streaming with cross-segment context
- WIP: NCCL Weight metadata transfer
- fix(memory): resolve UMA concurrent profiling race condition and page cache leak
- fix: tool_choice="required" falls back to tool_parser for non-JSON formats (streaming + non-streaming)
- [MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase
- [Bugfix] Safe CG padding for FlashMLA FP8 seq_lens and block_table
- [Bugfix] Fix DP port conflict race condition with late binding
- fix(compilation): optimize kv cache update for faster cold start compilation
- [Responses API] Sanitize leaked Harmony control tokens in tool names and recipients
- [Bug] Qwen3.5 GatedDeltaNet in_proj_ba fails Marlin MIN_THREAD_N=64 at TP>=4
- Docs
- Python not yet supported