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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Model] Reuse CUDA segments when loading Inkling expert weights
- [Bugfix][Model][CI/Build] Fix CUDA graph capture in GLM-OCR / GLM4-MoE-Lite MTP layers
- [Bug]: DeepSeek-V4-Flash: illegal memory access during FULL cudagraph capture (all-zero indexer seq_lens hit an OOB read in DeepGEMM's paged-MQA metadata kernel)
- [Bug]: Qwen3 MoE GPTQ `qzeros` shape mismatch on ROCm gfx1201
- [Core] Add per-request prefix-cache write policy
- [Bug]: security: bump minimum setuptools version in requirements/common.txt
- chore: Upstream Cohere parser fixes + tests
- [Bugfix] compressed-tensors: restore int8 grouped WNA16 MoE support
- [Bugfix] Reject FLASH_ATTN for fp8 KV cache when local attention forces FA2 fallback
- [Performance]: Erratic/poor DeepSeek V4 Pro MTP results on MI325X (gfx942) — ROCm kernels untuned
- Docs
- Python not yet supported