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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][MLA] Reach FULL cudagraphs for AITER MLA speculative decoding
- [Bugfix][Kernel] Fix divergent warp collectives in partial NeoX QK-Norm+RoPE
- [Refactor] Remove kernel dead code
- [Kimi-K3] MoRIIO KV transfer of hybrid mamba/KDA (conv+ssm) recurrent state (READ + WRITE)
- [Feature] Follow Up from inital ROCm DI CI enablement PR to break it up into smaller chunks - Nightly ROCm WideEP (EP>=16) DI CI
- [Build] Upgrade runtime image to Ubuntu 24.04, pick up rdma-core > 44
- [Bug]: Composite VLM wrapper (Mistral3ForConditionalGeneration) resolves tie_word_embeddings from the wrong (top-level) config, silently discarding a real lm_head.weight and producing coherent-vocabulary-but-incoherent output
- [CI Failure]: Kimi-Linear-48B-A3B Disaggregated DP EP
- [Profiler] Add Proton CUDA graph attribution
- [Profiler] Make distributed profiling transactional
- Docs
- Python not yet supported