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
- [Bug]: Concurrent temperature=0 non-determinism in vLLM, FLASH_ATTN batch-invariant path on Hopper
- [Kernel] Add Triton warmup compile-key tracing
- [RFC]: Extension points for backends whose physical layout isn't a permutation of the logical layout (weights, quant scales, KV-cache, MLA, EP)
- Revert "[MoE Refactor] Standardize Humming MoE experts + utilities" (#43373)
- Bump astral-sh/setup-uv from 7.6.0 to 9.0.0
- Enable FlashInfer + FP8 KV cache for text-only requests in Gemma 4 multimodal models
- [Bug] OOM during profile_run with GLM-5.2 PD disaggregation + FlashInfer CUTLASS MoE on H100
- [Bug] v0.24.0: DeepGEMM "Unknown recipe" assertion in FP8 kernel warmup on Blackwell (sm_120) — regression vs 0.23.0
- [Bug]: cached_tokens always equals prompt_tokens in disaggregated prefill (P/D) on the decode node
- [RFC]: Streaming Derender for Disaggregated Serving
- Docs
- Python not yet supported