]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog
pkg/ggml/sources/whisper.cpp
2024-11-15 Georgi Gerganovscripts : fix sync path
2024-11-15 Jhen-Jie Hongwhisper.swiftui : switch Mac dest to Mac (Designed...
2024-11-15 Georgi Gerganovcmake : fix ppc64 check (#0)
2024-11-15 Georgi Gerganovwhisper : include ggml-cpu.h (#0)
2024-11-15 Georgi Gerganovbuild : fixes
2024-11-15 Georgi Gerganovtalk-llama : sync llama.cpp
2024-11-15 Georgi Gerganovwhisper : fix build (#0)
2024-11-15 Georgi Gerganovsync : ggml
2024-11-15 Alberto Cabrera... sycl : Fixes to broken builds and test-backend-ops...
2024-11-15 Jeff Bolzvulkan: Optimize contiguous copies (llama/10254)
2024-11-15 Jeff Bolzvulkan: Throttle the number of shader compiles during...
2024-11-15 Georgi Gerganovmetal : more precise Q*K in FA vec kernel (llama/10247)
2024-11-15 Jeff Bolzvulkan: Fix newly added tests for permuted mul_mat...
2024-11-15 Georgi Gerganovmetal : reorder write loop in mul mat kernel + style...
2024-11-15 Georgi Gerganovmetal : fix build and some more comments (llama/10229)
2024-11-15 Georgi Gerganovmetal : fix F32 accumulation in FA vec kernel (llama...
2024-11-15 Georgi Gerganovmetal : hide debug messages from normal log
2024-11-15 SXXggml: fix zero division in ‘dne’ calculation in CUDA...
2024-11-15 amritahs-ibmggml : optimize llamafile cpu matrix multiplication...
2024-11-15 Georgi Gerganovmetal : opt-in compile flag for BF16 (llama/10218)
2024-11-15 Georgi Gerganovmetal : improve clarity (minor) (llama/10171)
2024-11-15 Georgi Gerganovmetal : optimize FA kernels (llama/10171)
2024-11-15 Diego Devesaggml : add ggml-cpu.h to the public headers (llama...
2024-11-15 snadampalfix q4_0_8_8 format for corrupted tokens issue (llama...
2024-11-15 Zhiyuan LiOptimize RWKV6 Operator Naming and Implement Multi...
2024-11-15 Georgi Gerganovmetal : add BF16 support (llama/8439)
2024-11-15 Diego Devesametal : fix from ptr buffer name (llama/10189)
2024-11-15 Georgi Gerganovggml : adjust is_first_call init value (llama/10193)
2024-11-15 Georgi Gerganovmetal : add quantized FA support (llama/10149)
2024-11-15 Diego Devesaggml : fix arch check in bf16_to_fp32 (llama/10164)
2024-11-15 EveQ6_K AVX improvements (llama/10118)
2024-11-15 Diego Devesaggml : fix gelu tables initialization (llama/10172)
2024-11-15 Diego Devesaggml : fix q4xx mat mul, increase ggml_aligned_malloc...
2024-11-15 snadampalfix build break on arm64 linux (llama/10166)
2024-11-15 Diego Devesacuda : clear error after changing peer access (llama...
2024-11-15 Georgi Gerganovmetal : simplify f16 and f32 dequant kernels (llama/0)
2024-11-15 Georgi Gerganovmetal : move dequantize templates to beginning of MSL...
2024-11-15 leo-ponyCANN: adjust backend registry refactor. (llama/10158)
2024-11-15 Diego Devesaggml : move CPU backend to a separate file (llama/10144)
2024-11-15 Georgi Gerganovmetal : minor fixup in FA kernel (llama/10143)
2024-11-15 Diego Devesallama : add simple-chat example (llama/10124)
2024-11-15 Diego Devesallama : use smart pointers for ggml resources (llama...
2024-11-15 Shupei Fanvulkan : improve ggml_vk_create_buffer error handling...
2024-11-15 Georgi Gerganovggml : remove ggml_scratch (llama/10121)
2024-11-15 Zhenwei Jinbuild: fix build error in Windows env with OneAPI setup...
2024-11-15 Diego Devesallama : fix buffer checks for mamba and rwk (llama...
2024-11-15 Diego Devesaggml : check tensor name lengths in gguf files (llama...
2024-11-15 Sergio Lópezkompute: add mul_mat_q4_k shader (llama/10097)
2024-11-15 Sergio Lópezkompute: add backend registry / device interfaces ...
2024-11-15 Diego Devesaggml : fix memory leaks when loading invalid gguf files...
2024-11-15 xctanggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (llama...
2024-11-15 Diego Devesallama : refactor model loader with backend registry...
2024-11-15 Changyeon Kimggml: Add POOL2D OP for GPU acceleration to the Vulkan...
2024-11-15 R0CKSTARmusa: workaround for Guilty Lockup in cleaning src0...
2024-11-15 Yuri Khrustalevcmake : make it possible linking ggml as external lib...
2024-11-15 Plamen Minevmetal : fix minor string leaks (ggml/1004)
2024-11-15 Georgi Gerganovscripts : update sync
2024-11-15 Raiya Arakici : fix building workflow for linux/arm64 container...
2024-11-13 KITAITI Makotoruby : extend API (#2551)
2024-11-13 Jhen-Jie Hongwhisper.swiftui : add model download list & bench metho...
2024-11-13 Wilson Silvaruby : fix the instructions (#2548)
2024-11-13 thewh1teagleggml : vulkan logs (#2547)
2024-11-13 Stefan Sydowexamples : fix ffmpeg v5 build (#2543)
2024-11-06 Vin Misrawhisper : fix extra memory usage (#2534)
2024-11-01 Georgi Gerganovwhisper : backend registry init before model load
2024-11-01 Georgi Gerganovtalk-llama : sync llama.cpp
2024-11-01 Georgi Gerganovsync : ggml
2024-11-01 Ma Mingfeiggml : add AMX backend (llama/8998)
2024-11-01 Georgi Gerganovmetal : support permuted matrix multiplicaions (llama...
2024-11-01 Johannes GäßlerCUDA: fix insufficient buffer clearing for MMQ (llama...
2024-11-01 Johannes GäßlerCUDA: fix MMQ for non-contiguous src0, add tests (llama...
2024-11-01 bssrdfincrease cuda_cpy block size (ggml/996)
2024-11-01 Jun Hee Yoometal : add POOL2D and fix IM2COL (llama/9943)
2024-11-01 leo-ponyAdapt to dynamically loadable backends mechanism (llama...
2024-11-01 Georgi Gerganovggml : add asserts for type conversion in fattn kernels...
2024-11-01 Radoslav Gerganovrpc : pack only RPC structs (llama/9959)
2024-11-01 Neo Zhang Jianyufix mul_mat_vec_q and *_vec_q error (llama/9939)
2024-11-01 Radoslav Gerganovrpc : backend refactoring (llama/9912)
2024-11-01 Ouadie EL FAROUKIAdd SYCL Backend registry, device and Event Interfaces...
2024-11-01 Ma Mingfeiadd amx kernel for gemm (llama/8998)
2024-11-01 Diego Devesavulkan : add backend registry / device interfaces ...
2024-11-01 Gilad Sfix: allocating CPU buffer with size `0` (llama/9917)
2024-11-01 Gilad Sfix: use `vm_allocate` to allocate CPU backend buffer...
2024-11-01 Johannes GäßlerCUDA: fix 1D im2col, add tests (ggml/993)
2024-11-01 leo-ponyFix cann compilation error (llama/9891)
2024-11-01 agray3Vectorize load instructions in dmmv f16 CUDA kernel...
2024-11-01 Diego Devesaggml : move more prints to the ggml log system (llama...
2024-11-01 Diego Devesarpc : add backend registry / device interfaces (llama...
2024-11-01 R0CKSTARmusa: add docker image support (llama/9685)
2024-11-01 Diego Devesaggml : fix BLAS with unsupported types (llama/9775)
2024-11-01 Diego Devesaggml : add backend registry / device interfaces to...
2024-11-01 Andrew Minh... Update building for Android (llama/9672)
2024-11-01 Georgi Gerganovggml : add metal backend registry / device (llama/9713)
2024-11-01 Paul Tsochantarismetal : single allocation of encode_async block (llama...
2024-11-01 Daniel Beveniusggml-alloc : remove buffer_id from leaf_alloc (ggml...
2024-10-31 Georgi Gerganovscripts : sync amx
2024-10-31 Georgi Gerganovggml : alloc ggml_contexts on the heap (#2525)
2024-10-30 Georgi Gerganovci : fix openblas build (#2511)
2024-10-29 Georgi Gerganovscripts : add turbo-q8_0 to the benchmark
2024-10-29 Georgi Gerganovwhisper : minor compile warning
next