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
- [Feature] Support prompt cache retention policies for tiered KV offloading
- [BugFix] Fix FunctionGemma streaming tool-call arguments corrupted once a 2nd key arrives
- [BugFix] Fix Jamba tool parser deleting all occurrences of the streamed prefix on tool transition
- [debug] 添加了eager 模式下的 权重hook
- [Bug]: [ROCm][gfx1201] AITER update in v0.25.0 generates unified-attention kernel exceeding LDS limit
- Rocm enable decoder cudagraph
- fix: reject required/named tool_choice for Harmony models without a tool parser
- [Model] Add minimal native RWKV7 serving support
- [Bug]: deepseek_v4 parser: reply without </think> routes the whole answer to reasoning_content (content empty), trailing EOS not stripped
- [Bugfix][Parser] Fix streaming tool-call args truncated by schema coercion
- Docs
- Python not yet supported