summaryrefslogtreecommitdiff
path: root/ggml-vulkan.cpp
AgeCommit message (Expand)Author
2024-05-28vulkan: properly initialize vulkan devices for LLAMA_SPLIT_MODE_NONE (#7552)k.h.lai
2024-05-23Update vulkan rope implementation to support frequency factors (#7475)0cc4m
2024-05-21llama : add phi3 128K model support (#7225)liuwei-git
2024-05-19Vulkan Embedding Fix (#7360)0cc4m
2024-05-18Update and fix Vulkan soft_max and argsort implementations (#7237)0cc4m
2024-05-11ggml : full ALiBi support (#7192)Georgi Gerganov
2024-05-09Vulkan Bugfixes and Improvements (#7084)0cc4m
2024-04-30ggml : add Flash Attention (#5021)Georgi Gerganov
2024-03-29Vulkan k-quant mmq and ggml-backend offload functionality (#6155)0cc4m
2024-03-26llama : greatly reduce output buffer memory usage (#6122)compilade
2024-03-18backend : offload large batches to GPU (#6083)slaren
2024-03-17ggml:fix finding transfer queue family index error (#6094)GainLee
2024-03-13llama : add pipeline parallelism support (#6017)slaren
2024-03-09ggml : remove old quantization functions (#5942)Georgi Gerganov
2024-03-05Vulkan Improvements (#5835)0cc4m
2024-03-04ggml : introduce ggml_status (ggml/750)Michael Podvitskiy
2024-03-01ggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was previously broken (#5813)ddpasa
2024-02-28make portability_enumeration_ext apple only (#5757)Eve
2024-02-28Introduce backend GUIDs (ggml/743)UEXTM.com
2024-02-25code : normalize enum names (#5697)Georgi Gerganov
2024-02-19Refactor validation and enumeration platform checks into functions to clean u...0cc4m
2024-02-19Add check for VK_KHR_portability_enumeration for MoltenVK support0cc4m
2024-02-19Add preprocessor checks for Apple devices.Mathijs de Bruin
2024-02-19Resolve ErrorIncompatibleDriver with Vulkan on MacOS.Mathijs de Bruin
2024-02-16cmake : fix VULKAN and ROCm builds (#5525)Georgi Gerganov
2024-02-15vulkan: Find optimal memory type but with fallback (#5381)Neuman Vong
2024-02-11vulkan: only use M-sized matmul on Apple GPUs (#5412)Sergio López
2024-02-09Fix Vulkan crash on APUs with very little device memory (#5424)0cc4m
2024-02-07Basic Vulkan Multi-GPU implementation (#5321)0cc4m
2024-02-03Vulkan Intel Fixes, Optimizations and Debugging Flags (#5301)0cc4m
2024-02-01Vulkan Phi Fix for AMD Proprietary Drivers (#5260)0cc4m
2024-01-31Vulkan Fixes (#5223)0cc4m
2024-01-30Vulkan Windows APU Memory Handling (#5199)0cc4m
2024-01-28ggml : add Vulkan backend (#2059)0cc4m