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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- int4 per-token-head KV cache: triton_reshape_and_cache_flash_per_token_head_quant returns wrong values
- [ROCm][Perf] Fuse DSA indexer QK preprocessing with AITER
- [Bug] NixlPushConnector heartbeat fails to renew KV leases
- fix(dflash-speculator): guard capture() log on needs_capture() (#53031)
- [Feature][Spec Decode] Carry auxiliary state across PP stages
- [ROCm][BugFix] Trim MoE GEMM input to valid token prefix
- [perf][MoE] flashinfer fp4 shared expert fusion
- [Bug]: draft model quant config never receives packed_modules_mapping — fused projections are built unquantized
- [ROCm] Disable AITER FP8/FP4 BMM for MLA by default
- [Bug]: CUDA graph memory profiling estimation is too huge
- Docs
- Python not yet supported