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
- [RFC]: Adaptive Speculation Depth for MoE Models via Per-Iteration Utility Budgeting
- [Bugfix][Frontend] Keep length finish_reason for max_tokens-truncated streaming tool calls
- [Bug]: gpu_memory_utilization is not respected on GB10 unified-memory systems during startup profiling (host wedges)
- [Feature] FlashAttention prefill-context-parallel (PCP) support for GQA
- [V1][Core] Add non-blocking get_output_nowait() to engine core client
- [GDN] Improve kkt kernel of CuteDSL prefill backend
- [Bug]: AssertionError: Expected a cached item for mm_hash
- [RFC]: Unify Context Parallelism in vLLM (PCP ⊥ DCP)
- [INC][ARK] Direct Register Custom Op for ARK
- [Bug]: Transcribing long audio that needs resampling fails — resample_audio_pyav overflows the int32 AudioFrame buffer, masked as "Invalid or unsupported audio file"
- Docs
- Python not yet supported