A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
main
[Model] Add Olmo3 model implementation (#24534)
Shane A committed about 1 year ago
[Frontend][Multimodal] Allow skipping media data when UUIDs are provided. (#23950)
Chenheli Hua committed about 1 year ago
[Core] Support async scheduling with uniproc executor (#24219)
Nick Hill committed about 1 year ago
[Qwen3Next] Fixes the cuda graph capture conditions under large batch sizes (#24660) (#24667)
Tao He committed about 1 year ago
Add FLASHINFER_MLA to backend selector test (#24753)
Matthew Bonanni committed about 1 year ago
[Attention][FlashInfer] Enable FP8 FlashInfer (TRTLLM) MLA decode (#24705)
Matthew Bonanni committed about 1 year ago
Invert pattern order to make sure that out_proj layers are identified (#24781)
Alexandre Marques committed about 1 year ago
[Compilation Bug] Fix Inductor Graph Output with Shape Issue (#24772)
Wentao Ye committed about 1 year ago
[Benchmark] Allow arbitrary headers to be passed to benchmarked endpoints (#23937)
Clayton Coleman committed about 1 year ago
[CI] Trigger BC Linter when labels are added/removed (#24767)
Zhewen Li committed about 1 year ago
[Bugfix] Fix incompatibility between #20452 and #24548 (#24754)
Cyrus Leung committed about 1 year ago
[CI] Speed up model unit tests in CI (#24253)
afeldman-nm committed about 1 year ago
[UX] Remove AsyncLLM torch profiler disabled log (#24609)
Michael Goin committed about 1 year ago
[Model] Switch to Fused RMSNorm in GLM-4.1V model (#24733)
Samit committed about 1 year ago
[Models] Prevent CUDA sync in Qwen2.5-VL (#24741)
Lukas Geiger committed about 1 year ago
[Models] Optimise and simplify `_validate_and_reshape_mm_tensor` (#24742)
Lukas Geiger committed about 1 year ago
[Bugfix][Frontend] Fix `--enable-log-outputs` does not match the documentation (#24626)
Kebe committed about 1 year ago
[Core] Shared memory based object store for Multimodal data caching and IPC (#20452)
dongluw committed about 1 year ago
[Qwen3-Next] MoE configs for H100 TP=1,2 and TP2/EP (#24739)
Elvir Crnčević committed about 1 year ago
[Bugfix] Fix MRoPE dispatch on XPU (#24724)
Yan Ma committed about 1 year ago