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 supported44 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Quantization] Per-shard FP8 scaling for MergedColumnParallelLinear
- [Bugfix][V1] KV cache: handle None block_size for Mamba/SSM groups
- [Kernel] Tune default fp8 block-scaled Triton config for M<=8 decode
- [Kernel] Add MixFP4 W4A16 Marlin inference support
- [Kernel] OAITritonExperts MXFP4: include SM 12.x in supported device range
- opt: merge_attn_states_kernel reuse scale via shared memory
- [V1][Bugfix] Reap EngineCore on parent death (#19849)
- Fix quant benchmarking script
- improve dynamic_per_token_scaled_fp8_quant_kernel_strided kernel
- [P/D][Mooncake] Add cross-layer KV cache support to MooncakeConnector
- Docs
- Python not yet supported