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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [v1] Guard resumable streaming updates against max_model_len overflow
- [Performance] DFlash slower than baseline at concurrency > 8 on Qwen3.5-35B-A3B
- [Bugfix] Fix async double streaming_update placeholder bug (#42490)
- [Bug]: Regression: vllm/vllm-openai:nightly fails to import nixl_ep due to missing libcudart.so.12
- Support weight-only quant for MX formats
- Remove unused CT formats and checks
- Remove per-block KV transfer error handling
- [Quant][Prototype] Hoist static FP8 input quant into model code
- [Bug]: Same-request resumable streaming_update can overflow prompt width in gpu_input_batch.add_request
- [Hardware][NVIDIA][Kernel] Add tuned Jetson AGX Orin / T234 MoE configs for Qwen3-30B-A3B-AWQ
- Docs
- Python not yet supported