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 supported59 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [DeepSeek-V3.2] Support sequence parallelism with pipeline parallelism
- [Bugfix] Load ModelOpt FP8 KV-cache scales into MLA attention
- [Bugfix] Map compressed-tensors KV-cache scale names for GPT-J
- [Docs] Clarify prefix-caching determinism expectations
- [Bugfix][ROCm][RDNA4] Snap the gfx1201 TRITON_ATTN decode split-K threshold to a capture size
- [Bugfix] Fix KV scale names on stacked models and the `--mm-encoder-only` shared root check
- [doc] out-of-tree quantization example imports FusedMoE, which the fused_moe package no longer exports
- [Perf][MoE] Skip DP padding rows in TRT-LLM monolithic MoE with vLLM's top-k
- [Performance]: Hybrid models with prefix caching prefill chunks above the default cudagraph capture ceiling eagerly
- [Perf][Quantization] Use fast SiLU intrinsics in Humming MoE activations
- Docs
- Python not yet supported