]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2025-07-01 R0CKSTARmusa: enable fp16 mma (all) and cublas on qy2 (llama...
2025-07-01 Aaron Teoggml-cpu: enable IBM NNPA Vector Intrinsics (llama...
2025-07-01 Sigbjørn Skjæretggml : do not output unprintable characters on GGUF...
2025-07-01 Anton Mitkovsycl: GGML_SYCL_DISABLE_OPT on by default for all Intel...
2025-07-01 lhezopencl: ref count `ggml_backend_opencl_context` and...
2025-07-01 uvosCUDA/HIP: optimize mmv paths taken for HIP devices...
2025-07-01 Johannes GäßlerCUDA: mul_mat_v support for batch sizes > 1 (llama...
2025-07-01 uvosHIP: enable vec fattn on RDNA4 (llama/14323)
2025-07-01 Aman GuptaCUDA: add mean operation (llama/14313)
2025-07-01 Markus TavenrathAdd support for VK_EXT_debug_utils to add labels to...
2025-07-01 Georgi Gerganovmetal : fix thread-safety (llama/14300)
2025-07-01 Aclyggml-cpu : "align corners" for bilinear upscale/downsca...
2025-06-25 Aclybuild : fix build with clang-cl on Windows (#1284)
2025-06-24 Daniel Beveniusggml-quants : rename best_mad to best_error (#1283)
2025-06-21 Georgi Gerganovtests : cleanup old tests (#1282)
2025-06-20 Georgi Gerganovsync : llama.cpp
2025-06-20 Aman GuptaCUDA: add conv_2d_transpose (llama/14287)
2025-06-20 Nicolò Scipionesycl: add usage of enqueue_functions extension (llama...
2025-06-20 Christian KastnerImplement GGML_CPU_ALL_VARIANTS for PowerPC (llama...
2025-06-20 Diego Devesacuda : synchronize graph capture and cublas handle...
2025-06-20 Georgi Gerganovggml : fix repack work size for mul_mat_id (llama/14292)
2025-06-20 Charles Xuggml: Update KleidiAI to v1.9.0 (llama/14277)
2025-06-20 Aman GuptaCUDA: add conv_2d_dw (llama/14265)
2025-06-20 Diego Devesaggml-cpu : remove unnecesary arm feature detection...
2025-06-20 fanyangbuild : suppress gcc15 compile warnings (llama/14261)
2025-06-20 Anton Mitkovsycl: Cleanup codepaths in Get Rows in sycl backend...
2025-06-20 Aaron Teollamafile : support s390x SIMD instruction set (llama...
2025-06-20 0cc4mVulkan: Set device max size for host memory to avoid...
2025-06-20 Georgi Gerganovmetal : add mean kernel (llama/14267)
2025-06-20 Aaron Teoggml-cpu: reduce asm calls for hsum (llama/14037)
2025-06-20 Aaron Teoggml-cpu: fix uncaught underscore terminators (llama...
2025-06-20 Charles Xuggml: Add Apple support for GGML_CPU_ALL_VARIANTS ...
2025-06-18 AclyAdd `ggml_roll` (#1274) upstream/0.0.2199
2025-06-18 Georgi Gerganovsync : whisper.cpp
2025-06-18 Georgi Gerganovsync : llama.cpp
2025-06-18 bandoticmake: remove shader-gen step-targets from ggml-vulkan...
2025-06-18 xctanggml-cpu : remove the weak alias trick (llama/14221)
2025-06-18 R0CKSTARmusa: fix build warning (unused variable) (llama/14231)
2025-06-18 Diego Devesallama : add thread safety test (llama/14035)
2025-06-18 bandoticmake: clean up external project logic for vulkan-shade...
2025-06-18 uvosHIP: disable rocwmma on gfx12 by default until rocm...
2025-06-18 Charles Xuggml: Add Android support for GGML_CPU_ALL_VARIANTS...
2025-06-18 Jeff Bolzvulkan: mutex around vkQueueSubmit (llama/14127)
2025-06-18 xctanggml-cpu : rework weak alias on apple targets (llama...
2025-06-18 uvosCUDA/HIP: fix ssm_scan on devices where warp size is...
2025-06-18 uvosHIP: Replace usage of depricated preprocessor macro...
2025-06-18 Anton Mitkovsycl: Adding additional cpy dbg print output (llama...
2025-06-18 Ewan CrawfordSYCL: Bump oneMath commit (llama/14152)
2025-06-18 Anton Mitkovsycl: Remove not needed copy f16->f32 for dnnl mul...
2025-06-18 Georgi Gerganovcmake : handle whitepsaces in path during metal build...
2025-06-18 Christian KastnerImplement GGML_CPU_ALL_VARIANTS for ARM (llama/14080)
2025-06-18 Jeff Bolzvulkan: Better thread-safety for command pools/buffers...
2025-06-18 Jeff Bolzvulkan: Track descriptor pools/sets per-context (llama...
2025-06-18 lhezopencl: add `mul_mv_id_q4_0_f32_8x_flat` (llama/14003)
2025-06-18 0cc4mVulkan: Don't default to CPU device (like llvmpipe...
2025-06-18 Isaac McFadyenrpc : nicer error messages for RPC server crash (llama...
2025-06-13 Daniel Beveniusggml : disable warnings for tests when using MSVC ...
2025-06-13 Daniel Beveniusggml : remove unused ggml_context_container (#1272)
2025-06-12 Daniel Beveniusscripts : remove common.{cpp,h} from whisper sync scrip...
2025-06-12 Daniel Beveniusexamples : include examples in msvc disable warn (...
2025-06-11 Daniel Beveniusmnist : use CMake to build mnist wasm example (#1269)
2025-06-10 Georgi Gerganovsync : whisper.cpp
2025-06-10 Georgi Gerganovggml : fix weak alias win32 (whisper/0)
2025-06-10 Georgi Gerganovfiles : remove old sources (part 2) (#1267)
2025-06-10 Georgi Gerganovfiles : remove old sources (#1266)
2025-06-10 Georgi Gerganovsync : llama.cpp
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...
2025-06-06 Daniel Beveniussam : add default case for unsupported prompt types...
2025-06-03 Kai PastorAdd in-build ggml::ggml ALIAS library (#1260)
2025-06-02 Radoslav Gerganovyolo : add support for dl backends (#1251)
2025-06-01 Georgi Gerganovsync : whisper.cpp
2025-06-01 Georgi Gerganovsync : llama.cpp
2025-06-01 Max Krasnyanskythreading: support for GGML_SCHED_PRIO_LOW, update...
2025-06-01 Shawn yangCUDA: add a prop in ggml_cuda_device_infor for distingu...
2025-06-01 Johannes GäßlerCUDA: fix typo in FlashAttention code (llama/13926)
2025-06-01 Diego Devesasched : avoid changing cur_copy when a graph is already...
2025-06-01 Diego Devesacuda : prevent using split buffers with 3d/4d matrices...
2025-06-01 Akarshan BiswasSYCL: Add mrope kernel (llama/13755)
2025-06-01 Christian Kastnercmake: Guard GGML_CPU_ALL_VARIANTS by architecture...
2025-06-01 Yibo Caiarm64: optimize q4_k_q8_k kernel with i8mm (llama/13886)
next