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
- fix: omit system_fingerprint key when fingerprint-mode=none
- [Bug]: Weight-loading/repacking memory is not reclaimed on discrete GPUs, forcing lower max-num-seqs / max-num-batched-tokens (Kimi K3, B200, fastsafetensors + DeepEP v2)
- [Bugfix][Scheduler] Preserve logprobs across streaming continuations
- DeepSeek-V4.1-Flash fails to start on 4x H20 (587GiB RAM): MEMCG OOM from host shmem (TP weight shards), not GPU
- [ROCm][DSv4.1] Add gfx950 FP4 compressed-KV paged attention
- [CPU] Add KDA backend for GLM5Next
- [Bug]: a error i can not find any stack
- [ROCm][Perf] Add AITER paged MXFP4 sparse indexing on gfx950
- LoRA device lookup falls through to packed weights when repacking clears weight
- [KVConnector][Mooncake] Add a failure ledger for the failure spine
- Docs
- Python not yet supported