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 auxiliary-GPU offloading for Qwen3.8-Flash-Next N-gram / PLE embeddings
- [Kernel][Qwen]Add qwen4 fuse op
- [Kernel] Fuse DeepEP-v2 decode globalize+align into one launch
- [Bug][DSV4][Blackwell SM12x] Indexer decode paged MQA logits broken when DeepGEMM is available: 2-state compress pages vs kernels templated for block_kv 32/64
- [Bugfix][Core] Restore constructor-only custom encoder cache manager support
- fix(parser): enforce required tool choice with gemma4 tool parser
- [Bug]: Profiler update does not integrate cleanly
- [Test] Conformance suite for KV-cache key partitioning
- [BugFix][Core] Promote parked skipped_waiting requests under saturation
- [Feature][KV cache] Support fine-grained prefix hits for sliding-window groups
- Docs
- Python not yet supported