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 16, 15:45 UTC
main
[Model] Support pp for qwen2-vl (#8696)
Yanyi Liu committed about 2 years ago
[Bugfix][CPU] fix missing input intermediate_tensors in the cpu_model_runner (#8733)
Li, Jiang committed about 2 years ago
[Hardware][CPU] Refactor CPU model runner (#8729)
Isotr0py committed about 2 years ago
[Core][Frontend] Support Passing Multimodal Processor Kwargs (#8657)
Alex Brooks committed about 2 years ago
[Bugfix] fix docker build for xpu (#8652)
Yan Ma committed about 2 years ago
[Bugfix] Fix CPU CMake build (#8723)
Luka Govedič committed about 2 years ago
[Bugfix] Avoid some bogus messages RE CUTLASS's revision when building (#8702)
Tyler Michael Smith committed about 2 years ago
[misc] upgrade mistral-common (#8715)
youkaichao committed about 2 years ago
[build] enable existing pytorch (for GH200, aarch64, nightly) (#8713)
youkaichao committed about 2 years ago
[SpecDec][Misc] Cleanup, remove bonus token logic. (#8701)
Lily Liu committed about 2 years ago
[Model][VLM] Add LLaVA-Onevision model support (#8486)
litianjian committed about 2 years ago
[MISC] rename CudaMemoryProfiler to DeviceMemoryProfiler (#8703)
Huazhong Ji committed about 2 years ago
[Misc] Use NamedTuple in Multi-image example (#8705)
Alex Brooks committed about 2 years ago
[Model] Refactor BLIP/BLIP-2 to support composite model loading (#8407)
Cyrus Leung committed about 2 years ago
[ci][build] fix vllm-flash-attn (#8699)
youkaichao committed about 2 years ago
[Bugfix] Refactor composite weight loading logic (#8656)
Isotr0py committed about 2 years ago
[Kernel][Bugfix] Delete some more useless code in marlin_moe_ops.cu (#8643)
Tyler Michael Smith committed about 2 years ago
[dbrx] refactor dbrx experts to extend FusedMoe class (#8518)
Divakar Verma committed about 2 years ago
rasmith committed about 2 years ago
[Doc] Fix typo in AMD installation guide (#8689)
Andy Dai committed about 2 years ago