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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KVCache] Support model specific KVCache planning
- Add DeepSeek-V4 FIM completion rendering
- [Bugfix] Fix speculative decoding for short_conv (LFM2) models
- [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: 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]: [Bug] Severe GPU Memory Leak and OOM with Native KV Offloading in Multi-Node PP=2 TP=8 Setup (v0.22.0)
- [Bug]: when set kv_cache_dtype to fp8 or fp8_e4m3 causes the d node to crash
- Docs
- Python not yet supported