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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix use_existing_torch.py removing unrelated packages
- [Bugfix] Add batched experts auto-upgrade for VLLM_FLASHINFER_MOE_BACKEND path
- fix: create DeepGEMM JIT cache directory before import
- [Bug]: gpt-oss no output with TRITON_ATTN backend with spec decode on ROCm
- [SimpleCPUOffloadConnector]: Add support for reset_cache()
- [Bug]: GLM-5 tool calls in stream mode get error tool name
- [WIP] Support Allreduce + Norm + Per-token Group Fp8 Quant Fusion
- [Bug]:CUDA illegal instruction during decode (V1 Engine + NVFP4) on aarch64 (NVIDIA GB10)
- [Bug]: Check if the vLLM API server port is already in use.
- replace torch.cuda.set_stream with accelerator api
- Docs
- Python not yet supported