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
- [Bugfix][CI] Fix `ImportError: libcudart.so.12: cannot open shared object file: No such file or directory`
- [Bug]: Non-deterministic KV-cache reservation on hybrid GDN model (Qwen3.6) → CUDA-graph capture OOMs after /health passes → restart crash-loop (native full RTX 5090 / sm120)
- [RFC]: hardware agnostic model definitions in vLLM
- [RFC]: Semantic KV Cache Reuse Interface
- [Kernel] Add optional TileLang backend for bf16 activation-and-mul ops
- fix(__init__): validate colon separator in logits processor FQCN strings
- [Bugfix] Restore device placement for repl_token_ids in Qwen3-VL EVS video embeddings
- fix(internlm2_tool_parser): prevent ValueError when output has multiple tool-call markers
- fix(logits_processor): raise user-friendly ValueError when FQCN lacks ':' separator
- Fix(rope): preserve rope_theta in rope_parameters when loading transformers v5 checkpoints with transformers v4
- Docs
- Python not yet supported