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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Qwen3.5 AWQ models crash during inference on RTX 5090 (Blackwell) with Triton OOM in solve_tril despite successful model load
- [Bugfix] Fix cpu-offload-gb assertion with non-default block sizes
- [Bug]: Qwen3.5-27B fails to start with CPU KV cache offloading (`--kv_offloading_backend native`) while Qwen3-32B works fine
- [Usage]: How to use Env in yaml
- [Bug]: vllm 0.17.0 启动Qwen3.5-122B-A10B失败
- [Feature]: will support qwen3.5-eagle3 deployment?
- [Bugfix] Enable bitwise invariance for mxfp4 MoE matmul_ogs kernel
- [Bug]: The hit rate of prefix caching in Qwen3.5 35BA3B is very low, always less than 0.1%
- [Bug]: pip install 0.17 fails with CXXABI_1.3.15 not found
- [Bug]: Negative prompt token counter crashes engine under CPU KV offloading + high concurrency
- Docs
- Python not yet supported