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]: More control over expert parallelism (--moe_ep_size, --moe_tp_size)
- [Bug]: Qwen3-32B use eagle3 crash
- [Feature]: Batch invariant: Enable TRITON_MLA with prefix-caching
- [Bug]: sagemaker_sessions on a shared cluster
- [CI][ROCm] (wip) Fix test_async_scheduing
- [RFC]: Add SJF Scheduling Policy
- suppport pcp & dcp
- [Hybrid] Remove use of PAD_SLOT_ID for causal_conv_1d
- [ROCm][FEAT] Support Decode Context Parallelism for ROCM_AITER_FA Backend
- [Bug]: MemoryError throw by transformers_utils.utils module's parse_safetensors_file_metadata function when loading some gptq or awq quantization models since vllm 0.11.1
- Docs
- Python not yet supported