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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- test(quantization): cover tied lm_head/embed_tokens when lm_head excluded from ModelOpt
- [Model] Add minimal native RWKV7 serving support
- [Bug]: deepseek_v4 parser: reply without </think> routes the whole answer to reasoning_content (content empty), trailing EOS not stripped
- [Bugfix] Fix HYV3 shared_mlp prefix for compressed-tensors ignore matching
- [Bugfix][Parser] Fix streaming tool-call args truncated by schema coercion
- [Bugfix] Make Gemma 4 suppress-token masking CUDA-graph safe
- [Bugfix] Avoid FlashAttention 3 with batch invariance on Hopper
- [Bugfix] Share FlashInfer B12x MoE workspace across layers
- Dynamic-fork scheduling, Medusa/MTP spec decode, and InternVL resize for HPD-Parsing (based on v0.17.1)
- [RFC]: GDS support for filesystem KV-cache offloading
- Docs
- Python not yet supported