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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Sanitize server file paths from validation error responses
- [ROCm][Test] xfail fused TRITON MXFP4 MoE accuracy on gfx950
- [ROCm][Perf] Fused shared expert for Minimax M3
- [ROCm] honour skip_kv_gather in AITER MLA sparse prefill chunk loop (#40018)
- [AMD] Revert `Mxfp4MoeBackend.TRITON_UNFUSED` fallback
- [Benchmark] Add Gumbel sampler benchmark for speculative decoding
- Patch 4
- [2/N][Core] support partial prefix cache hits in hybrid coordinator
- [Core] Add CuMemAllocator.discard() for tag-selective GPU memory release
- Fix multimodal cache desync after input rejection
- Docs
- Python not yet supported