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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Use NVFP4 packed layout for SlidingWindowSpec.real_page_size_bytes
- [ROCm] Disable AITER allreduce fusion for HIP graph replay
- [MM][Perf][CG] Support ViT full CUDA graph for InternVL
- Fix #30128
- Fix: merge default stop_token_ids with request stop_token_ids in to_sampling_params
- [Bug]: FLASH_ATTN_DIFFKV crashes on init with
- [ROCm][Perf] Fix RMSNorm+Quant fusion for gfx950 (non-fnuz)
- [Quantization] Add ModelOpt NVFP4 W4A16 (4-bit weights, fp16/bf16 activations) support
- [Model Runner V2] FP32 gumbel sampling.
- Add multimodal embed task-prefix docs and tests
- Docs
- Python not yet supported