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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: gfx1100 (RDNA3): first-call non-determinism + long-seq corruption from Triton paged-attention fallback (ROCm 7.14)
- [Bugfix] Honour VLLM_MQ_MAX_CHUNK_BYTES_MB at every MessageQueue call site
- [ROCm]: Bump torch 2.12, triton 3.7, torchaudio, torchvision
- [Bugfix] Fix NVFP4 shape mismatch in flashinfer_scaled_fp4_mm #50557
- [Quantization][ModelOpt] Serve modelopt_mixed checkpoints with FP8_PB layers
- [Bugfix][NIXL] Include transfer mode (push/pull) in the compatibility hash
- [Bugfix] Drop the -1 dcp_world_size sentinel in MLACommonImpl
- [Bugfix] [Rust Frontend] Stream Kimi K3 tool-call arguments incrementally
- [ROCm][MLA] Make num_kv_splits occupancy-aware for Triton MLA decode
- [Bugfix] Guard mhc_pre_broadcast_tilelang on DeepGEMM support
- Docs
- Python not yet supported