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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: [XPU] compressed-tensors WNA16 MoE selector ignores XPU platform, crashes on Marlin path
- [ROCm][DeepSeek-V4] WIP: Enable CSA multistream decode
- [RFC]:
- [RFC]: Streaming API for Real-Time Server State and Metrics
- chore: improve vllm maintenance path
- [LoRA][Bugfix] register lora_linear_async op unconditionally
- [Bugfix] Reject mamba_block_size not divisible by 8
- [Bug]: AssertionError at kv_cache_utils.py:1042 — dense draft model + hybrid-attention main (DeltaNet+SWA) fails in unify_kv_cache_spec_page_size
- [Bug]: enforce_eager=False will generate garbage tokens for InternVL2-8B
- [Bug]: DeepSeek-V4-Flash-FP8 crashes consistently after processing partial benchmark requests with data parallel and expert parallel (vLLM v0.20.1, H200)
- Docs
- Python not yet supported