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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Revert "[Perf] Wire silu_and_mul_per_block_quant into TritonFP8MoE (MiniMax-M2)" (#42497)
- docs: clarify CUDA nightly wheel index priority
- Revert "[MM][CG] Enable encoder Cudagraph for Step3VL" (#42224)
- draft: routing replay for monolithic trtllm FlashInfer MoE kernels
- Support Nomic-embed-text-v1 with transformers v5
- [feature] [xgrammar] support `patternProperties` and `propertyNames` kw for object types
- [ROCm][Perf] Enabled FP4Indexer for DSV4
- [Bug]: "The page size of the layer is not divisible by the maximum page size" When serving Qwen3.5 MoE with custom "VLLM_PP_LAYER_PARTITION"
- [bugfix] Add package name to vllm setup.py
- [Bug]: DeepSeek-V4-Flash for L20,RuntimeError: Worker failed with error 'AssertionError: auto_functionalized was not removed', please check the stack trace above for the root cause
- Docs
- Python not yet supported