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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: GLM 5.2 Performance Optimization
- Fix write-after-write hazard in xpu KV RoPE triton kernel
- [Bug]: test_logprobs.py::test_spec_decode_logprobs not using eager mode even though comment says it is
- [Core][V1] Support trace_decode_token_ids for deterministic decode replay
- Update FA pin to have new FA2 not pull in dropout headers
- [Bug] DeepSeekV4-Flash produces incorrect output with inline system messages after PR #46025 when `preserved in-place`
- Enable gfx1250 ROCm architecture
- [HelionLinearBackend][3/N] Add HelionFP8ScaledMMLinearKernel
- [DBO] Disallow DBO in multinode deployments when using the DeepEP High Throughput all2all backend.
- Enable humming wNaM assymetric quant (zero_point) wih compressed-tensors
- Docs
- Python not yet supported