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
- [Bugfix][LoRA] Avoid block_n=128 for lora_expand on Hopper
- fix: Add FP8 type dispatch to per_token_group_quant_8bit for transformers backend
- [MRV2][Spec Decode] Adaptive Speculative Decoding - Initial Support
- [Bug]: [ROCm][gfx1201] AITER update in v0.25.0 generates unified-attention kernel exceeding LDS limit
- Rocm enable decoder cudagraph
- fix: reject required/named tool_choice for Harmony models without a tool parser
- 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
- Docs
- Python not yet supported