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 supported45 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Turbo Quant keep failing TRITON_ATTN 'kv_cache_dtype not supported'
- [Feature]: Support logging the complete request prompt and model output to the log for easier debugging.
- [Feat][KVConnector] Refresh CPU LRU cache for eager offloading
- [Bug]: In case chunked prefill is enabled and max-num-batched-tokens > max-model-length the server does not start up and fails
- [Feature]: Priority scheduling supports preemption of requests in the running queue by requests in the waiting queue
- [Tracking issue]: TurboQuant/HIGGS Attention follow-ups
- [Bugfix] Fix TurboQuant KV cache index-out-of-bounds in Triton decode kernel
- [Performance] Stagger checkpoint file reads across ranks to reduce I/O contention
- fix: prevent streaming sessions from exceeding max_model_len
- [SimpleCPUOffloadConnector]: Support cross layer KV layout
- Docs
- Python not yet supported