]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog
pkg/ggml/sources/whisper.cpp
7 days ago Georgi Gerganovtalk-llama : sync llama.cpp
7 days ago Georgi Gerganovsync : ggml
7 days ago Aman GuptaCUDA: add conv_2d_transpose (llama/14287)
7 days ago Nicolò Scipionesycl: add usage of enqueue_functions extension (llama...
7 days ago Christian KastnerImplement GGML_CPU_ALL_VARIANTS for PowerPC (llama...
7 days ago Diego Devesacuda : synchronize graph capture and cublas handle...
7 days ago Georgi Gerganovggml : fix repack work size for mul_mat_id (llama/14292)
7 days ago Charles Xuggml: Update KleidiAI to v1.9.0 (llama/14277)
7 days ago Aman GuptaCUDA: add conv_2d_dw (llama/14265)
7 days ago Diego Devesaggml-cpu : remove unnecesary arm feature detection...
7 days ago fanyangbuild : suppress gcc15 compile warnings (llama/14261)
7 days ago Anton Mitkovsycl: Cleanup codepaths in Get Rows in sycl backend...
7 days ago Aaron Teollamafile : support s390x SIMD instruction set (llama...
7 days ago 0cc4mVulkan: Set device max size for host memory to avoid...
7 days ago Georgi Gerganovmetal : add mean kernel (llama/14267)
7 days ago Aaron Teoggml-cpu: reduce asm calls for hsum (llama/14037)
7 days ago Aaron Teoggml-cpu: fix uncaught underscore terminators (llama...
7 days ago Charles Xuggml: Add Apple support for GGML_CPU_ALL_VARIANTS ...
7 days ago AclyAdd `ggml_roll` (ggml/1274)
9 days ago Daniel Beveniusandroid : update CMakeLists.txt to use FetchContent...
9 days ago Georgi Gerganovcmake : fix android build (#3265)
9 days ago Daniel Beveniusexamples : add stereo to mono conversion in read_audio_...
10 days ago Georgi Gerganovtalk-llama : sync llama.cpp
10 days ago Georgi Gerganovsync : ggml
10 days ago bandoticmake: remove shader-gen step-targets from ggml-vulkan...
10 days ago xctanggml-cpu : remove the weak alias trick (llama/14221)
10 days ago R0CKSTARmusa: fix build warning (unused variable) (llama/14231)
10 days ago Diego Devesallama : add thread safety test (llama/14035)
10 days ago bandoticmake: clean up external project logic for vulkan-shade...
10 days ago uvosHIP: disable rocwmma on gfx12 by default until rocm...
10 days ago Charles Xuggml: Add Android support for GGML_CPU_ALL_VARIANTS...
10 days ago Jeff Bolzvulkan: mutex around vkQueueSubmit (llama/14127)
10 days ago xctanggml-cpu : rework weak alias on apple targets (llama...
10 days ago uvosCUDA/HIP: fix ssm_scan on devices where warp size is...
10 days ago uvosHIP: Replace usage of depricated preprocessor macro...
10 days ago Anton Mitkovsycl: Adding additional cpy dbg print output (llama...
10 days ago Ewan CrawfordSYCL: Bump oneMath commit (llama/14152)
10 days ago Anton Mitkovsycl: Remove not needed copy f16->f32 for dnnl mul...
10 days ago Georgi Gerganovcmake : handle whitepsaces in path during metal build...
10 days ago Christian KastnerImplement GGML_CPU_ALL_VARIANTS for ARM (llama/14080)
10 days ago Jeff Bolzvulkan: Better thread-safety for command pools/buffers...
10 days ago Jeff Bolzvulkan: Track descriptor pools/sets per-context (llama...
10 days ago lhezopencl: add `mul_mv_id_q4_0_f32_8x_flat` (llama/14003)
10 days ago 0cc4mVulkan: Don't default to CPU device (like llvmpipe...
10 days ago Isaac McFadyenrpc : nicer error messages for RPC server crash (llama...
10 days ago Daniel Beveniusggml : disable warnings for tests when using MSVC ...
10 days ago Daniel Beveniusggml : remove unused ggml_context_container (ggml/1272)
10 days ago Daniel Beveniusexamples : include examples in msvc disable warn (ggml...
10 days ago Daniel Beveniuswhisper : clear result_all if vad_samples is empty...
11 days ago Daniel Beveniusexamples : set the C++ standard to C++17 for server...
12 days ago w1redch4dexamples : update usage/help in yt-wsp.sh (#3251)
12 days ago Sacha Arbonelserver : graceful shutdown, atomic server state, and...
2025-06-13 Daniel Beveniuswhisper : fix VAD processing for skipped audio segments...
2025-06-13 Daniel Beveniusserver : add Voice Activity Detection (VAD) support...
2025-06-13 Daniel Beveniuscli : fix short name conflict for vad options [no ci...
2025-06-13 Daniel Beveniusruby : add .gitignore entries for ext directory (#3245)
2025-06-11 Daniel Beveniusci : update windows runner to windows-2022 (#3242)
2025-06-10 Daniel Beveniusruby : add cleaning of library names in dependencies...
2025-06-10 Georgi Gerganovggml : fix weak alias win32 (#0)
2025-06-10 Georgi Gerganovandroid : fix builds (#0)
2025-06-10 Georgi Gerganovsync : ggml
2025-06-10 Georgi Gerganovfiles : remove old sources (part 2)
2025-06-10 Georgi Gerganovsync : ggml
2025-06-10 Georgi Gerganovfiles : remove old sources
2025-06-10 Georgi Gerganovtalk-llama : sync llama.cpp
2025-06-10 Georgi Gerganovsync : ggml
2025-06-10 Georgi Gerganovmetal : use less stack memory in FA kernel (llama/14088)
2025-06-10 xctanggml-cpu : split arch-specific implementations (llama...
2025-06-10 Diego Devesacuda : fix device sync on buffer clear (llama/14033)
2025-06-10 Xinpeng DouCANN: Simplify the environment variable setting(#13104)
2025-06-10 Nicolò Scipionesycl: Add reorder to Q6_K mmvq implementation (llama...
2025-06-10 Diego Devesacuda : fix buffer type check with integrated GPUs ...
2025-06-10 Akarshan BiswasSYCL: Implement few same quantized type copy kernels...
2025-06-10 Masato Nakasakavulkan: Enable VK_KHR_cooperative_matrix extension...
2025-06-10 Diego Devesallama : allow using mmap without PrefetchVirtualMemory...
2025-06-10 Jeff Bolzvulkan: automatically deduce size of push constants...
2025-06-10 Ervin Áron... ggml-vulkan: adds support for op CONV_TRANSPOSE_1D...
2025-06-10 Diego Devesareleases : use dl backend for linux release, remove...
2025-06-10 Johannes GäßlerCUDA: fix FTZ in FA for Gemma 3 (llama/13991)
2025-06-10 Jeff Bolzvulkan: fix warnings in perf logger querypool code...
2025-06-10 lhezopencl: add `backend_synchronize` (llama/13939)
2025-06-10 rmatifOpenCL: Add concat, tsembd, upscale, tanh, pad and...
2025-06-10 Georgi Gerganovmetal : use F32 accumulators in FA kernels (llama/13975)
2025-06-10 shalinib-ibmcmake : Handle mixed-case 'Power' strings in POWER...
2025-06-10 Atharva Dubeysycl: quantize and reorder the input to q8_1 when reord...
2025-06-10 Johannes Gäßlergguf: fix failure on version == 0 (llama/13956)
2025-06-10 Aaron Teoggml: check if non-native endian model is being loaded...
2025-06-10 Kai PastorAdd in-build ggml::ggml ALIAS library (ggml/1260)
2025-06-10 KITAITI Makotoruby : output format (#3237)
2025-06-09 藍+85CDci : build and publish main-intel image (#3231)
2025-06-06 藍+85CDdocker : add main-intel dockerfile (#3229)
2025-06-04 KITAITI Makotoruby : Add parallel transcription support (#3222)
2025-06-03 Daniel Beveniusci : add mirror for ports.ubuntu.com (ARM packages...
2025-06-03 Joas Devbindings.java : apply whisperParams in fullTranscribeWi...
2025-06-03 R0CKSTARmusa: correct MUSA SDK rc4.0.1 download URL (#3217)
2025-06-02 Daniel Beveniusci : use mirrors.kernel.org for Ubuntu packages (#3220)
2025-06-02 Daniel Beveniusnode : add language detection support (#3190)
2025-06-01 Georgi Gerganovtalk-llama : sync llama.cpp
2025-06-01 Georgi Gerganovsync : ggml
2025-06-01 Max Krasnyanskythreading: support for GGML_SCHED_PRIO_LOW, update...
next