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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Revert "[Bugfix] mamba: run single-token extends as decodes (#42430)"
- [Performance]: Triton fusion for Qwen2/3-MoE shared-expert gate (Qwen2MoeMLP/Qwen3MoeMLP)
- fix(chat): allow multimodal content in tool messages for vision models
- [Bugfix] Fix DeepSeek V4 ImportError when cutlass/quack versions are incompatible
- [Usage]: DeepSeek-V4 startup takes ~8 min — guidance on reducing initialization time
- [Bugfix][Reasoning] Properly detect reasoning end when using thinking_token_budget
- [DO NOT MERGE][Perf][DSv4] Add generic cuteDSL LL Blockwise FP8 GEMM with PDL
- Refactor CT NVFP4 linear schemes around reusable weight/activation bu…
- [Bug]: ZeroDivisionError in deepgemm_post_process_fp8_weight_block when loading FP8 model with TP=16 on dual-node H20
- 【Feature】Modify the fps parameter when loading the multimodal model Video.
- Docs
- Python not yet supported