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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Support MLA attention + quant fusions
- [Bug]: Enabling speculative coding causes malformed Tool Calls in Qwen 122B MXFP4
- [Feature]: Performance Tuning of FlashInfer MLA Sparse
- [Kernel] Add FP8 block-quantized MoE config for E=256,N=512 on H100
- [Performance]: The checkpoint you are trying to load has model type `qwen3_5` but Transformers does not recognize this architecture.
- [Bug]: NameError: 'IntermediateTensors' is not defined in GPT-OSS model during Pipeline Parallelism
- Feat/scaled fp4 quant use functional
- [Quark] Support loading Quark NVFP4 checkpoints in vLLM
- [Core] Add structured request_id to log records
- [MoE Refactor] Remove SharedFusedMoE class
- Docs
- Python not yet supported