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
- [Attention] Support `fp8_ds_mla` in Triton MLA on Ampere
- [ROCm][KV Connector] Add MoRIIO transfer stats and Prometheus metrics
- [Bug]: Responses API rejects `input_text` content for Mistral Large 4 with --tokenizer-mode mistral
- [ROCm][DSv4.1] Read V4.1 KV records in Mono decode on gfx950
- [XPU] Use xccl2 backend for XPU distributed communication
- [Kernel][Fusion] Fuse tanh-GELU gated activation with static FP8 quant
- [ROCm][CI] Fix GPU memory startup flakes in PP and sleep mode tests
- [Core][Mamba] Keep align-mode Mamba state in fixed block-table slots on MRV2
- Proposal: packed KV-cache block stride for unequal per-group page sizes (1.7366x planner, byte-identical tokens)
- [Misc] Use torch 2.14 custom class API for LayerName registration
- Docs
- Python not yet supported