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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Clear conflicting structured outputs in strict tool calling
- [Bugfix][Kimi] Preserve dotted tool names and strip streamed argument whitespace
- [Bugfix][Kimi] Surface raw output when a tool-call section parses no calls
- [Bugfix][Frontend] Avoid KeyError in tool_choice validation for tools missing a function key
- [Bug]: Kimi 2.5 response formatting error / corrupted JSON output with huge whitespaces under high concurrency (H20)
- Bug Fix: Correct Device Detection for pin_memory in Packed/MoE LoRA Adapters
- BUG: ValueError (not enough values to unpack) when logits processor FQCN is missing ':' separator
- Bug: missing colon in logits processor FQCN crashes engine init with unhelpful ValueError
- [Feature Request] Memory Poisoning Protection for vLLM Serving via OWASP Agent Memory Guard
- [Bug]: Linear host RSS growth + step-up in E2E latency under sustained `max_tokens=1` classification load (Gemma-3-1b, V1, prefix caching)
- Docs
- Python not yet supported