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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] [ROCm] Add gfx12x FP8 support for fused_batched_moe kernels
- [Test] Add nightly MoE eval tests
- [BugFix]Fix the bug where query_start_loc values are polluted/corrupted in _dummy_run
- Handle capped SWA admission in allocator path
- PERF (DeepSeek): Multi-stream overlap of indexer wk+weights_proj with QKV-A for DeepSeek V3.2 NSA
- [Bugfix] Fix uniform_batch for same-sized prefills
- [Performance]Reduce cpu launch overheads for MultiGroupBlockTable and attn_meta_data handling on Blackwell
- [Attention][SM90] Add CUTLASS FA3 sparse MLA attention backend for Hopper GPUs
- [Feature] Fused SiLU + Mul + per-token dynamic FP8 quantization (Triton)
- INT16/FP8/INT8 + SR SSM Cache Support
- Docs
- Python not yet supported