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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Attention][MiniMax-M3] Add FlashInfer MSA backend for SM90 and SM120/SM121
- [Bugfix] Added CUDA graph capturing enabled flag management in MRV2
- [CI Failure]: Entrypoints Integration - test_derender_parity.py::test_inline_derender_parity[n2]
- [Bugfix][DSv4.1] Run decoder replay on a PP stage that starts at the cut
- [Bugfix][Spec Decode] Don't specialize MRV2 _gather_draft_sampled_kernel on num_logits
- [ROCm][CI] Run `/ci rocm cache` on the ci pipeline instead of AMD CI
- [HiSparse] Flush hot-buffer stats on the metrics logging timescale
- [ROCm][DSv4/4.1] Enable Tensor scale FP8 KV Cache for Sparse MLA
- [Perf][DSv4.1] Reuse the gathered compressed KV across consumers in FlashMLA prefill
- [Kernel] Deferred RecoverSSM verify kernels for FP32-state KDA layers
- Docs
- Python not yet supported