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 supported30 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][DSV4][Kernel] Add gfx950 HIP compressor path
- [Tool Parser] Fix make_valid_python backslash-escape edge case
- [Rust Frontend] Add longcat tool parser support
- [torch.compile] fix misleading docstrings in non-impacting config compute_hash (#39479 item 7)
- [CPU] Fix shared-memory all-reduce deadlock across nodes
- tests(v1): add enforce_eager=True to test_spec_decode_logprobs
- [RFC]: Reduce multimodal payload in token-in/token-out by deferring `pixel_values` preprocessing to `/generate`
- [Rust Frontend] Avoid redundant decode per token in incremental detokenizer
- [Attention] Occupancy-gated 3D segmented decode for multi-query (diffusion-LM canvas) over long KV
- [Bugfix] Avoid MLA decode shared memory OOR
- Docs
- Python not yet supported