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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][DSV4.1] Make the fused all-reduce + mHC token cap configurable
- [ROCm][Kimi-K3] Keep the AttnRes block bank in a persistent workspace
- [ROCm][Perf][DSA] Honor skip_kv_gather in the ROCm sparse-indexer prefill loop
- [Bugfix][KV Connector][MoRIIO] WRITE: keep the RDMA completion wait off the forward thread and fail only the affected request
- [Rust Frontend] engine client interface
- [ROCm][DSv4.1] Avoid runtime JIT for offset combine_topk_swa_indices inputs
- [ROCm][Perf][Kimi-K3] DSpark Markov sampling sharded over the vocabulary, one launch
- [Quantization][OOT] Fix OnlineQuantizationConfig overriding the registered OOT online quantization config
- [Bugfix] Fix P2P ZMQ reconnect dropped while the ROUTER still holds the old routing id
- [Kernel][Perf] Run DeepGEMM Mega MoE on SM90 with MXFP4 experts
- Docs
- Python not yet supported