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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Revert "[BugFix] Fix packed HND KV cache reshape for FlashAttention" (#47314)
- Revert "[Misc] Use meta tensor for KV cache stride calculation" (#47316)
- [Bug]: InternLM2 streaming tool parser loses arguments (or the whole tool call) when the call arrives in a single delta
- [Rust Frontend] Add Granite4 and Hermes4 tool roundtrips
- feat: extended EPLB support for Mistral Large 3 and additional MoE backends
- Pin RMSNorm block size under batch-invariant mode
- [Model] Add Nemotron Ministral masked block-diffusion LM
- [Bugfix] Emit added/done lifecycle events for zero-delta streaming items
- Skip layerwise reload for non-quantized models
- TRITON_MLA_SPARSE fallback crashes on SM80 during CUDA graph capture
- Docs
- Python not yet supported