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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Build] Use pip constraints to pin dependency versions
- Add `moe_align_block_size_no_permute` for small batch size with large num_expert
- custom build backend
- WIP - Paged Eviction
- [Feature][Cleanup]: Unify `vllm.utils.flashinfer` and `vllm.model_executor.layers.quantization.utils.flashinfer_utils`
- [Feature]: Error Logging Redesign
- [Usage]: CPU offload still results in out of VRAM error (Unsloth's DeepSeek R1)
- replace `with torch.cuda.stream()`
- [12/n] Migrate hadamard + mamba to torch stable ABI
- Allow other models to use the Harmony format
- Docs
- Python not yet supported