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
- Fix/gemma4 nvfp4 per expert
- DeepSeekv4 ROCm Optimization
- [Model] Support TranslateGemma-12b-it
- [On hold] feat(kernels): Migrate mm_encoder_attn to vLLM IR
- Implement custom dataset class for ASR benchmarking
- [Bug]: compressed-tensors W4A16 MoE: weight_scale not sharded along K under tensor parallelism, kernel computes wrong group_size
- [Bug]: the A800 architecture cannot start the glm5.1 model.
- [Bug]: TP Worker hang causes EngineDeadError - RPC call to sample_tokens timed out (DeepSeek-V4-Pro, TP=8, MTP speculative decoding)
- [DSV4] Attention accumulation in model dtype
- RFC: Memory-backend interface for KV cache hot paths and attention decode
- Docs
- Python not yet supported