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
- [ROCm][Perf][MLA] Use AITER Triton bf16 BMM for the decode W_UV when tuned
- [Bugfix] Graph profiling retained workspace
- [Bugfix][Benchmark] Reject colliding sweep figure filenames
- Optimize TP MoE collectives via output projection sharding
- [Core][DBO] Dual batch overlap under pure tensor parallelism (split PR of M3.1)
- [Bugfix][Spec Decode] Keep FlashInfer CUDA graphs for drafters with their own head count
- [ROCm][Kimi-K3] Enable encoder graph capture for Kimi-K3 Vision Tower
- [Attention][MLA] Add NVFP4 KV cache for dense MLA with FlashInfer Cake decode
- [ROCm][Perf][DSv4] GFX1250 A8W8 Blockscale GEMM preshuffled + shared_experts fused_clamp_act_mul
- [ROCm][Quantization][Perf] Fuse the block Hadamard input rotation into AITER's MXFP4 activation quant
- Docs
- Python not yet supported