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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: MI300/MI325 DeepSeekv4 Pro (Functional Support & Recipes)
- [ROCm] Enable ROCm Attention Sinks and Connector-Friendly KV Layouts
- [Frontend] Add site-packages support for reasoning/tool parser plugins
- feat(ec-connector): async multimodal embedding-cache loading — scheduler hold-back for PENDING embeddings
- [Bugfix] Pre-compile _zero_kv_blocks_kernel and _compute_slot_mapping_kernel during warmup
- [Tests][Reasoning] Add test coverage for Step3ReasoningParser
- [Bugfix][Frontend] Keep a reference to the background abort task in disagg api_router
- [MM][CG] Support ViT full CUDA graph for Ernie-4.5-VL image inference
- [Bug]: max-num-seqs is not accurate when using async scheduling (especially affects P-D disaggregation prefills)
- [RFC]: FULL cudagraph support for spec-decode drafter chain steps (currently PIECEWISE-only; measured ~15-18% of decode step time)
- Docs
- Python not yet supported