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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: gpt-oss-120b MXFP4 MoE init OOM-killed on unified-memory ARM (DGX Spark / Jetson Thor)
- [Kernel][ROCm] Cover OCP MX MoE emulation in the mxfp4 oracle test
- [Bug]: Qwen3.6-27B-FP8 on GB10: get_output() spin-loop on stuck CUDA stream during prefill burst (run<6, KV<5%)
- MLA: kv_b_proj.weight.dtype AttributeError on quantized ColumnParallelLinear in chunked prefill
- [Bugfix][DeepSeekV4] Handle optional scale tensors for W4A16-FP8 artifacts
- fix: avoid ZeroDivisionError in FP8 scaled MM kernels with high TP (closes #43174)
- Validate num_gpu_blocks_override in CacheConfig
- [Bugfix][SM121] Extend TrtLlmFp8ExpertsBase device gate to SM_12x (consumer Blackwell / DGX Spark)
- [Parity with CUDA]: Add top 5-10 popular OSS models into mi355, mi325, mi300 into vLLM nightly performance & accuracy regression testing & dashboard
- [RFC]: Move trainer-side weight transfer logic out of `vllm`
- Docs
- Python not yet supported