git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog

]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog

overview / pkg / ggml / sources / whisper.cpp / shortlog

2025-09-20	Chenguang Li	CANN: Support eager execution mode under ACL graph...	commit \| commitdiff \| tree
2025-09-20	hipudding	CANN: Support ext_factor in rope (llama/15710)	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	ggml-backend: raise GGML_MAX_SPLIT_INPUTS (llama/15722)	commit \| commitdiff \| tree
2025-09-20	Gilad S	vulkan: use memory budget extension to read memory...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: add missing clamps in new mul_mat_id paths...	commit \| commitdiff \| tree
2025-09-20	Ruben Ortlam	vulkan: disable large mmv subgroups on older Nvidia...	commit \| commitdiff \| tree
2025-09-20	s-goto-11	ggml: SVE support for exponential functions (llama...	commit \| commitdiff \| tree
2025-09-20	Prashant Vithule	ggml: aarch64: Implement SVE F16 kernels for vector...	commit \| commitdiff \| tree
2025-09-20	Ruben Ortlam	Vulkan: Add Integer Dot Product mul_mat_vec shader...	commit \| commitdiff \| tree
2025-09-20	Daniel Bevenius	ggml : WebGPU add TRANSPOSE and RESHAPE to supported...	commit \| commitdiff \| tree
2025-09-20	Akarshan Biswas	CUDA: fix build error from ambiguous __half conversions...	commit \| commitdiff \| tree
2025-09-20	hipudding	CANN: Optimize MUL_MAT_ID (llama/15658)	commit \| commitdiff \| tree
2025-09-20	hipudding	CANN: fix RoPE cache issue on multi-device (llama/15629)	commit \| commitdiff \| tree
2025-09-20	Georgi Gerganov	metal : fix checks for available FA kernels (llama...	commit \| commitdiff \| tree
2025-09-20	Diego Devesa	llama : separate compute buffer reserve from fattn...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: handle large sizes for get_rows (llama/15686)	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: mul_mat_id coopmat2 optimizations (llama/15546)	commit \| commitdiff \| tree
2025-09-20	Daniel Bevenius	vulkan : remove unused portability_enumeration_ext...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: Allow fallback to sysmem memory when vidmem...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: clamp matmul and FA results to the max finite...	commit \| commitdiff \| tree
2025-09-20	Charles Xu	ggml: update kleidiai to v1.13.0 (llama/15663)	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	llama: use FA + max. GPU layers by default (llama/15434)	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	CUDA: use FP32 arithmetic for conv2d (llama/15683)	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: Skip syncing for prealloc_y when it is reused...	commit \| commitdiff \| tree
2025-09-20	Chenguang Li	CANN: FIx compiler warnings (llama/15661)	commit \| commitdiff \| tree
2025-09-20	Aman Gupta	CUDA: fix bug in rms_norm fusion (llama/15660)	commit \| commitdiff \| tree
2025-09-20	Aman Gupta	CUDA: fuse adds, fuse add with rms norm (llama/15631)	commit \| commitdiff \| tree
2025-09-20	mnehete32	CUDA: add conv2d (llama/15635)	commit \| commitdiff \| tree
2025-09-20	Aaron Teo	ggml-cpu: fix invalid hsum build in debug s390x (llama...	commit \| commitdiff \| tree
2025-09-20	compilade	ggml : fix SSM_SCAN for n_groups > 1 (llama/15625)	commit \| commitdiff \| tree
2025-09-20	Georgi Gerganov	kv-cache : remove LLAMA_SET_ROWS checks (llama/15505)	commit \| commitdiff \| tree
2025-09-20	matiaslin	cuda: Add cublasLt_static linking when GGML_STATIC...	commit \| commitdiff \| tree
2025-09-20	uvos	HIP: Enable support for ggml_backend_cuda_register_host...	commit \| commitdiff \| tree
2025-09-20	Chenguang Li	CANN: refactor mask handling and improve performance...	commit \| commitdiff \| tree
2025-09-20	xctan	ggml-cpu : add basic RVV support for vector f32 ops...	commit \| commitdiff \| tree
2025-09-20	rmatif	OpenCL: add fused group_norm/norm, mul, add (llama...	commit \| commitdiff \| tree
2025-09-20	Akarshan Biswas	SYCL: fix rms_norm_mul_add for tensor dim not a multipl...	commit \| commitdiff \| tree
2025-09-20	shalinib-ibm	llamafile: PowerPC Sgemm Optimization (llama/15558)	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	CUDA: return -1 for nonexistent compiled arch (llama...	commit \| commitdiff \| tree
2025-09-20	Georgi Gerganov	metal : optimize FA vec for large sequences and BS...	commit \| commitdiff \| tree
2025-09-20	Georgi Gerganov	metal : improve `MUL_MAT_ID` (llama/15541)	commit \| commitdiff \| tree
2025-09-20	Sigbjørn Skjæret	metal : remove contiguous assertion for src0 in IM2COL...	commit \| commitdiff \| tree
2025-09-20	Yoshi_likes_e4	Add a warning for special devices (llama/15563)	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: Remove splitting for mul_mat_id (llama/15568)	commit \| commitdiff \| tree
2025-09-20	Qeeweew	CUDA: Accelerate MXFP4 table lookup using `__byte_perm...	commit \| commitdiff \| tree
2025-09-20	lhez	opencl: fix support ops condition for `rms_norm` (llama...	commit \| commitdiff \| tree
2025-09-20	Ruben Ortlam	vulkan: fix min subgroup 16 condition for mmid subgroup...	commit \| commitdiff \| tree
2025-09-20	Ihar Hrachyshka	metal: fix regression when no metal devices are present...	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	CUDA: MoE helper in device code, better tile sizes...	commit \| commitdiff \| tree
2025-09-20	Georgi Gerganov	metal : add FA kernels for HS=40 (llama/15559)	commit \| commitdiff \| tree
2025-09-20	Chenguang Li	CANN: ROPE cache sin/cos repeat (llama/15501)	commit \| commitdiff \| tree
2025-09-20	Ruben Ortlam	vulkan: apply MUL_MAT_ID subgroup optimization to non...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: Support FA with any multiple of 8 head sizes...	commit \| commitdiff \| tree
2025-09-20	Ruben Ortlam	vulkan: enable Conv2D for Apple after MoltenVK fixed...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: workaround MoltenVK compile failure in multi_ad...	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	CUDA: fix half2 -> half conversion for HIP (llama/15529)	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: optimize rms_norm, and allow the work to spread...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: Rewrite synchronization to allow some overlap...	commit \| commitdiff \| tree
2025-09-20	Acly	vulkan : support ggml_mean (llama/15393)	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: optimize mul_mat_id loading row ids into shared...	commit \| commitdiff \| tree
2025-09-20	Reese Levine	ggml WebGPU: add support for quantization types (llama...	commit \| commitdiff \| tree
2025-09-20	rmatif	ggml: add `conv3d` op (llama/15182)	commit \| commitdiff \| tree
2025-09-20	Yavor Ivanov	cuda : add Pad Reflect 1D support (llama/14659)	commit \| commitdiff \| tree
2025-09-20	Aaron Teo	ggml-cpu: Support Q5_0 and Q5_1 on s390x (llama/15486)	commit \| commitdiff \| tree
2025-09-20	Chenguang Li	CANN: Optimize RMS_NORM using cache (llama/15419)	commit \| commitdiff \| tree
2025-09-20	Diego Devesa	sched : fix possible use of wrong ids tensor when offlo...	commit \| commitdiff \| tree
2025-09-20	Acly	vulkan : support conv_2d_dw with f16 weights (llama...	commit \| commitdiff \| tree
2025-09-20	Dong Won Kim	vulkan: add exp operation (llama/15456)	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: Reuse conversion results in prealloc_y (llama...	commit \| commitdiff \| tree
2025-09-20	Xuan-Son Nguyen	ggml : fix condition of im2col on Metal backend (llama...	commit \| commitdiff \| tree
2025-09-20	R0CKSTAR	musa: add GGML_UNUSED_VARS (llama/15446)	commit \| commitdiff \| tree
2025-09-20	Diego Devesa	sched : copy only the used experts when offloading...	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	CUDA: refactor FA support/selection code (llama/15454)	commit \| commitdiff \| tree
2025-09-20	Johannes Gäßler	CUDA: replace GGML_CUDA_F16 with CUDA arch checks ...	commit \| commitdiff \| tree
2025-09-20	Jeff Bolz	vulkan: shorten pipeline name strings (llama/15431)	commit \| commitdiff \| tree
2025-09-20	R0CKSTAR	musa: fix build warnings (llama/15258)	commit \| commitdiff \| tree
2025-09-20	lhez	opencl: mark `argsort` unsupported if cols exceed workg...	commit \| commitdiff \| tree
2025-09-20	SHUAI YANG	CANN: optimize rope operator (llama/15335)	commit \| commitdiff \| tree
2025-09-20	R0CKSTAR	musa: handle __hgt2_mask, available starting from MUSA...	commit \| commitdiff \| tree
2025-09-20	Marvin Gießing	ggml-cpu: add mxfp4 VSX intrinsics for Power9+ (ppc64le...	commit \| commitdiff \| tree
2025-09-20	Georgi Gerganov	cuda : remove obsolete sources (ggml/1332)	commit \| commitdiff \| tree
2025-09-19	Carlos Zoido	ggml : Fix MKL detection by quoting BLAS_INCLUDE_DIRS...	commit \| commitdiff \| tree
2025-09-08	Siva Mahadevan	whisper : prefer curl over wget in download scripts...	commit \| commitdiff \| tree
2025-09-05	Daniel Bevenius	ci : remove brew installation of cmake for macos-latest...	commit \| commitdiff \| tree
2025-09-04	Daniel Bevenius	tests : use CMake definitions for model/sample paths...	commit \| commitdiff \| tree
2025-08-24	Treboko	Handle negative value in padding (#3389)	commit \| commitdiff \| tree
2025-08-24	Thea Mukhi	models : update`./models/download-ggml-model.cmd`...	commit \| commitdiff \| tree
2025-08-18	Georgi Gerganov	talk-llama : sync llama.cpp	commit \| commitdiff \| tree
2025-08-18	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-08-18	Reese Levine	ggml: Add initial WebGPU backend (llama/14521)	commit \| commitdiff \| tree
2025-08-18	Aaron Teo	ggml : initial zDNN backend (llama/14975)	commit \| commitdiff \| tree
2025-08-18	Georgi Gerganov	common : handle mxfp4 enum	commit \| commitdiff \| tree
2025-08-18	compilade	ggml-quants : fix make_qp_quants NANs and IQ1 assertion...	commit \| commitdiff \| tree
2025-08-18	Jeff Bolz	vulkan: disable spirv-opt for bfloat16 shaders (llama...	commit \| commitdiff \| tree
2025-08-18	Jeff Bolz	vulkan: Use larger workgroups for mul_mat_vec when...	commit \| commitdiff \| tree
2025-08-18	Dong Won Kim	vulkan: support sqrt (llama/15370)	commit \| commitdiff \| tree
2025-08-18	Jeff Bolz	vulkan: Optimize argsort (llama/15354)	commit \| commitdiff \| tree
2025-08-18	Jeff Bolz	vulkan: fuse adds (llama/15252)	commit \| commitdiff \| tree
2025-08-18	Jeff Bolz	vulkan: Support mul_mat_id with f32 accumulators (llama...	commit \| commitdiff \| tree
2025-08-18	Jeff Bolz	vulkan: Add missing bounds checking to scalar/coopmat1...	commit \| commitdiff \| tree
next

Packaging of ggerganov/whisper.cpp

RSS Atom