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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Perf] Deduplicate tokenizer.decode() calls in logprobs detokenization
- [Bugfix][KVConnector] Include prompt_embeds digest in LMCacheMP cache key
- [Bugfix][V1][MoE] Warm up WNA16 MoE Triton kernels
- [Bugfix][Mooncake] Fix DP worker bootstrap register ReadTimeout race
- [Model Runner V2] Fix `seq_lens_cpu_upper_bound`
- [Bugfix] Allow disable_any_whitespace with auto backend
- [ModelRunnerV2] Avoid pipeline parallel bubbles
- [Perf] Apply single-pass min_larger finding and binary search in Triton Top-p path.
- refactor(flashinfer, DCP): fix the order of seq_lens_cpu/np handling in FlashInferMetadataBuilder
- [Metrics] Add group-aware KV cache capacity Prometheus gauges
- Docs
- Python not yet supported