]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2024-11-19 Romain Biessysycl : Add option to set the SYCL architecture for...
2024-11-19 Jeff Bolzvulkan: Optimize soft_max (llama/10301)
2024-11-19 Alberto Cabrera... sycl: Revert MUL_MAT_OP support changes (llama/10385)
2024-11-19 Diego Devesacuda : only use native when supported by cmake (llama...
2024-11-19 Jeff Bolzvulkan: remove use of null initializer (llama/10372)
2024-11-18 Plamen Minevmetal : fox offset integer overflows in im2col (#1015)
2024-11-18 Georgi Gerganovsync : llama.cpp
2024-11-18 0cc4mVulkan: Fix device info output format specifiers (llama...
2024-11-18 PABmetal : add `GGML_UNARY_OP_ELU` kernel (#1018)
2024-11-18 Georgi Gerganovsync : llama.cpp
2024-11-18 Johannes GäßlerCUDA: fix MMV kernel being used for FP16 src1 (llama...
2024-11-18 Georgi Gerganovsync : llama.cpp
2024-11-18 Johannes GäßlerCMake: fix typo in comment [no ci] (llama/10360)
2024-11-18 Diego Devesallama : only use default buffer types for the KV cache...
2024-11-18 Georgi Gerganovmetal : refactor kernel args into structs (llama/10238)
2024-11-18 FirstTimeEZggml : fix undefined reference to 'getcpu' (llama/10354)
2024-11-18 Johannes GäßlerCUDA: remove DMMV, consolidate F16 mult mat vec (llama...
2024-11-18 Johannes GäßlerCMake: default to -arch=native for CUDA build (llama...
2024-11-18 Diego Devesaggml : fix possible buffer use after free in sched...
2024-11-18 Georgi Gerganovggml : inttypes.h -> cinttypes (llama/0)
2024-11-18 Georgi Gerganovggml : adapt AMX to tensor->grad removal (llama/0)
2024-11-18 Georgi Gerganovggml : fix compile warnings (llama/0)
2024-11-18 Georgi Gerganovllamafile : fix include path (llama/0)
2024-11-18 Jeff Bolzvulkan: Optimize some mat-vec mul quant shaders (llama...
2024-11-18 Dan Johanssonggml : optimize Q4_0 into Q4_0_X_Y repack (llama/10324)
2024-11-18 Srihari-mcwMake updates to fix issues with clang-cl builds while...
2024-11-16 Johannes Gäßlerggml: new optimization interface (#988)
2024-11-15 Georgi Gerganovggml : remove duplicated sources from the last sync...
2024-11-15 Georgi Gerganovsync : llama.cpp
2024-11-15 slarenggml : fix some build issues
2024-11-15 Georgi Gerganovsync : leftovers (#0)
2024-11-15 Georgi Gerganovtest-dup : minor fix
2024-11-15 Georgi Gerganovcmake : restore CMakeLists.txt (llama/10256)
2024-11-15 EveAVX BF16 and single scale quant optimizations (llama...
2024-11-15 Romain Biessysycl: Use syclcompat::dp4a (llama/10267)
2024-11-15 Charles Xubackend cpu: add online flow for aarch64 Q4_0 GEMV...
2024-11-15 Diego Devesaggml : build backends as libraries (llama/10256)
2024-11-15 Georgi Gerganovscripts : update sync llama.cpp
2024-11-15 Georgi Gerganovsync : whisper.cpp
2024-11-15 Georgi Gerganovcmake : fix ppc64 check (whisper/0)
2024-11-15 thewh1teagleggml : vulkan logs (whisper/2547)
2024-11-13 Georgi Gerganovsync : llama.cpp
2024-11-13 Alberto Cabrera... sycl : Fixes to broken builds and test-backend-ops...
2024-11-13 Jeff Bolzvulkan: Optimize contiguous copies (llama/10254)
2024-11-13 Jeff Bolzvulkan: Throttle the number of shader compiles during...
2024-11-13 Georgi Gerganovmetal : more precise Q*K in FA vec kernel (llama/10247)
2024-11-13 Jeff Bolzvulkan: Fix newly added tests for permuted mul_mat...
2024-11-13 Georgi Gerganovmetal : reorder write loop in mul mat kernel + style...
2024-11-13 Georgi Gerganovmetal : fix build and some more comments (llama/10229)
2024-11-13 Georgi Gerganovmetal : fix F32 accumulation in FA vec kernel (llama...
2024-11-13 Georgi Gerganovmetal : hide debug messages from normal log
2024-11-13 SXXggml: fix zero division in ‘dne’ calculation in CUDA...
2024-11-13 amritahs-ibmggml : optimize llamafile cpu matrix multiplication...
2024-11-13 Georgi Gerganovmetal : opt-in compile flag for BF16 (llama/10218)
2024-11-13 Georgi Gerganovmetal : improve clarity (minor) (llama/10171)
2024-11-13 Georgi Gerganovmetal : optimize FA kernels (llama/10171)
2024-11-08 Georgi Gerganovsync : llama.cpp
2024-11-08 Diego Devesaggml : add ggml-cpu.h to the public headers (llama...
2024-11-08 snadampalfix q4_0_8_8 format for corrupted tokens issue (llama...
2024-11-08 Zhiyuan LiOptimize RWKV6 Operator Naming and Implement Multi...
2024-11-08 Georgi Gerganovmetal : add BF16 support (llama/8439)
2024-11-08 Diego Devesametal : fix from ptr buffer name (llama/10189)
2024-11-08 Georgi Gerganovggml : adjust is_first_call init value (llama/10193)
2024-11-08 Georgi Gerganovmetal : add quantized FA support (llama/10149)
2024-11-08 Diego Devesaggml : fix arch check in bf16_to_fp32 (llama/10164)
2024-11-08 EveQ6_K AVX improvements (llama/10118)
2024-11-04 Georgi Gerganovsync : llama.cpp
2024-11-04 Diego Devesaggml : fix gelu tables initialization (llama/10172)
2024-11-04 Diego Devesaggml : fix q4xx mat mul, increase ggml_aligned_malloc...
2024-11-04 snadampalfix build break on arm64 linux (llama/10166)
2024-11-04 Diego Devesacuda : clear error after changing peer access (llama...
2024-11-04 Georgi Gerganovmetal : simplify f16 and f32 dequant kernels (llama/0)
2024-11-04 Georgi Gerganovmetal : move dequantize templates to beginning of MSL...
2024-11-04 leo-ponyCANN: adjust backend registry refactor. (llama/10158)
2024-11-04 slarenupdate tests and examples
2024-11-04 Georgi Gerganovsync : llama.cpp
2024-11-04 Diego Devesaggml : move CPU backend to a separate file (llama/10144)
2024-11-04 Georgi Gerganovmetal : minor fixup in FA kernel (llama/10143)
2024-11-04 Diego Devesallama : add simple-chat example (llama/10124)
2024-11-04 Diego Devesallama : use smart pointers for ggml resources (llama...
2024-11-04 Shupei Fanvulkan : improve ggml_vk_create_buffer error handling...
2024-11-04 Georgi Gerganovggml : remove ggml_scratch (llama/10121)
2024-11-04 Zhenwei Jinbuild: fix build error in Windows env with OneAPI setup...
2024-11-04 Diego Devesallama : fix buffer checks for mamba and rwk (llama...
2024-11-04 Diego Devesaggml : check tensor name lengths in gguf files (llama...
2024-11-04 Sergio Lópezkompute: add mul_mat_q4_k shader (llama/10097)
2024-11-04 Sergio Lópezkompute: add backend registry / device interfaces ...
2024-11-04 Diego Devesaggml : fix memory leaks when loading invalid gguf files...
2024-11-04 xctanggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (llama...
2024-11-04 Diego Devesallama : refactor model loader with backend registry...
2024-11-04 Changyeon Kimggml: Add POOL2D OP for GPU acceleration to the Vulkan...
2024-11-04 R0CKSTARmusa: workaround for Guilty Lockup in cleaning src0...
2024-11-04 Georgi Gerganovscripts : update sync
2024-11-02 Yuri Khrustalevcmake : make it possible linking ggml as external lib...
2024-11-01 Plamen Minevmetal : fix minor string leaks (#1004)
2024-11-01 Georgi Gerganovsync : whisper.cpp
2024-11-01 Georgi Gerganovggml : alloc ggml_contexts on the heap (whisper/2525)
2024-10-26 Georgi Gerganovggml : remove sync artifacts
2024-10-26 Ma Mingfeiggml : add AMX backend (llama/8998)
2024-10-26 Georgi Gerganovsync : llama.cpp
next