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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- refactor hard coded device string in test files under tests/v1 and tests/lora
- [Bugfix] Fix for builtins (forward fix of pytorch/177558)
- Fix ambiguous num_blocks for hybrid attn mamba
- Add nvfp4 support to reshape_and_cache_flash
- [Bug]: gdn prefill kernel errors
- [torch.compile] Refactor Attention Quant Fusion Pass and Remove Boilerplate
- [3/n] Migrate cutlass/scaled_mm_entry.cu torch stable ABI
- Fix `redundancy_buffer_memory` not taken account in `determine_available_memory()`
- [Responses API] tool_choice support (auto / required / none) for GPT-OSS
- support firered_aed_l model
- Docs
- Python not yet supported