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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Attention] Reject TORCH_SDPA for decoder attention
- [Bugfix][Structured Output] Preserve raw scores before grammar masking
- [Bugfix][Kernel] Plan b12x NVFP4 W4A16 linear token counts at load time
- [DeepSeek-V4] Warm up DeepGEMM fp8_einsum for the o_proj
- [Bugfix][Prefix] Skip EAGLE block drop for KV-shared drafters + widen periodic SWA tail
- [Rust Frontend] Support beam search (use_beam_search, length_penalty)
- [Feature][Core] Reset prefix cache without preempting running requests
- [XPU] Use xccl2 backend for XPU distributed communication
- [ROCm][CI] Fix GPU memory startup flakes in PP and sleep mode tests
- [ROCm][RDNA][Perf] W4A16: fused scale/zero-point carrier for Triton prefill
- Docs
- Python not yet supported