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
- [Bug]: fp8_blockscale_gemm JIT compilation fails on vLLM Docker image — missing cublasLt.h, nvrtc.h, and -lnvrtc
- [Bugfix] Add missing clip_qkv implementation to OLMoE attention
- [Feature]: Support serving ModelOpt W4A8 MXFP4+FP8 checkpoints
- [Misc] Fix stale doc URL and docstring module path
- [CI] Improve (NCCL and torch) symmetric memory allreduce test coverage
- [CI Failure]: Import error in test_utils.py
- [RFC]: Batch-Aware Expert Pruning for MoE Decode (XShare)
- [Bug]: MXFP4A16 compressed-tensors quantization produces degenerate output (PPL 22,953 vs 8.74 BF16)
- [Bug]: Subset of Lora unit tests fail on NVIDIA VLLM Stack
- CUDA illegal memory access in MoE layer with MiniMax-M2.5 NVFP4 on Blackwell (SM120)
- Docs
- Python not yet supported