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

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

overview / pkg / ggml / sources / ggml / shortlog

2025-07-12	Georgi Gerganov	sync : resolve conflicts (#0)	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: support SET_ROWS (llama/14587)	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: optimizations for deepseek prompt processing...	commit \| commitdiff \| tree
2025-07-12	Tarek Dakhran	model : support LiquidAI LFM2 hybrid family (llama...	commit \| commitdiff \| tree
2025-07-12	Slobodan Josic	HIP : Add HIP 7.0+ compatibility for hipBLAS compute...	commit \| commitdiff \| tree
2025-07-12	rmatif	opencl: add tiled mul_mat_f16_f32 (llama/14535)	commit \| commitdiff \| tree
2025-07-12	lhez	opencl: add `set_rows` for `f16` and `f32` (llama/14547)	commit \| commitdiff \| tree
2025-07-12	Aman Gupta	Docs: script to auto-generate ggml operations docs...	commit \| commitdiff \| tree
2025-07-12	Akarshan Biswas	SYCL: Initial set_rows kernel implementation (llama...	commit \| commitdiff \| tree
2025-07-12	compilade	cuda : support Falcon-H1 state size for SSM_SCAN (llama...	commit \| commitdiff \| tree
2025-07-12	Xuan-Son Nguyen	ggml : add ggml_scale_bias (llama/14417)	commit \| commitdiff \| tree
2025-07-12	Miaoqian Lin	ggml : prevent integer overflow in gguf tensor size...	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: optimize flash attention split_k_reduce (llama...	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan : fix rope with partial rotation and non-cont...	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	cuda : fix rope with partial rotation and non-cont...	commit \| commitdiff \| tree
2025-07-12	Aman Gupta	CUDA: add bilinear interpolation for upscale (llama...	commit \| commitdiff \| tree
2025-07-12	R0CKSTAR	musa: fix build warnings (unused variable) (llama/14561)	commit \| commitdiff \| tree
2025-07-12	Aman Gupta	CUDA: add bf16 and i32 to getrows (llama/14529)	commit \| commitdiff \| tree
2025-07-12	Eve	vulkan: increase LOAD_VEC_A to 8 (IQ1/IQ2) or 4 (IQ3...	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: fix rms_norm+mul fusion (llama/14545)	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: Handle updated FA dim2/3 definition (llama...	commit \| commitdiff \| tree
2025-07-12	Sigbjørn Skjæret	opencl: add GELU_ERF (llama/14476)	commit \| commitdiff \| tree
2025-07-12	R0CKSTAR	test-backend-ops: add support for specifying output...	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	metal : disable fast math in all quantize kernels ...	commit \| commitdiff \| tree
2025-07-12	luyhcsu	CANN: Replace aclrtMemsetSync with aclnnInplaceZero...	commit \| commitdiff \| tree
2025-07-12	Sigbjørn Skjæret	ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama...	commit \| commitdiff \| tree
2025-07-12	lhez	opencl : broadcast for soft_max (llama/14510)	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: support mixed/deepseekR1 FA head sizes (llama...	commit \| commitdiff \| tree
2025-07-12	Johannes Gäßler	ggml: backward pass for split swiglu (llama/14483)	commit \| commitdiff \| tree
2025-07-12	Nicolò Scipione	Fix conditional enabling following arch checks for...	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	kv-cache : use ggml_set_rows (llama/14285)	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	ggml : fix FA mask dim 2 and 3 (llama/14505)	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	ggml : remove kompute backend (llama/14501)	commit \| commitdiff \| tree
2025-07-12	Aman Gupta	CUDA: add dynamic shared mem to softmax, refactor gener...	commit \| commitdiff \| tree
2025-07-12	compilade	llama : initial Mamba-2 support (llama/9126)	commit \| commitdiff \| tree
2025-07-12	Aman Gupta	CUDA: add softmax broadcast (llama/14475)	commit \| commitdiff \| tree
2025-07-12	Johannes Gäßler	CUDA: broadcasting for FlashAttention mask (llama/14500)	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: support softmax/FA batch and broadcast (llama...	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	ggml : support bcast ggml_soft_max_ext, ggml_flash_attn...	commit \| commitdiff \| tree
2025-07-12	zhouwg	opencl : fix possible buffer overflow in dump_tensor...	commit \| commitdiff \| tree
2025-07-12	Eric Zhang	opencl : skip empty nodes on cgraph compute (llama...	commit \| commitdiff \| tree
2025-07-12	lhez	opencl : update upscale to support align corners (llama...	commit \| commitdiff \| tree
2025-07-12	Björn Ganster	ggml : Callback before abort (llama/14481)	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	ci : disable fast-math for Metal GHA CI (llama/14478)	commit \| commitdiff \| tree
2025-07-12	Chenguang Li	CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmul...	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: Split large mul_mat_id to fit in shared memory...	commit \| commitdiff \| tree
2025-07-12	Sigbjørn Skjæret	add GELU_ERF (llama/14455)	commit \| commitdiff \| tree
2025-07-11	Kai Pastor	ci : simplify, switch to ninja (#1295)	commit \| commitdiff \| tree
2025-07-10	Kai Pastor	examples : Test installed CMake config package (#1294)	commit \| commitdiff \| tree
2025-07-03	Acly	vulkan : implement bilinear interpolation for ggml_upsc...	commit \| commitdiff \| tree
2025-07-03	Acly	vulkan : implement ggml_roll (#1290)	commit \| commitdiff \| tree
2025-07-02	Daniel Bevenius	ggml : add version function to get lib version (#1286)	commit \| commitdiff \| tree
2025-07-02	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2025-07-01	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-07-01	Georgi Gerganov	ggml : remove trailing whitespace (llama/0)	commit \| commitdiff \| tree
2025-07-01	lhez	opencl : add GEGLU, REGLU, SWIGLU (llama/14456)	commit \| commitdiff \| tree
2025-07-01	Aman Gupta	Add Conv2d for CPU (llama/14388)	commit \| commitdiff \| tree
2025-07-01	Georgi Gerganov	metal : disable fast-math for some cpy kernels (llama...	commit \| commitdiff \| tree
2025-07-01	Romain Biessy	ggml-cpu: sycl: Re-enable exp f16 (llama/14462)	commit \| commitdiff \| tree
2025-07-01	Diego Devesa	test-backend-ops : disable llama test (llama/14461)	commit \| commitdiff \| tree
2025-07-01	xiaobing318	cmake : Remove redundant include path in CMakeLists...	commit \| commitdiff \| tree
2025-07-01	Vedran Miletić	scripts : make the shell scripts cross-platform (llama...	commit \| commitdiff \| tree
2025-07-01	Akarshan Biswas	SYCL: disable faulty fp16 exp kernel (llama/14395)	commit \| commitdiff \| tree
2025-07-01	Sigbjørn Skjæret	ggml : fix unmerged GGML_FPxx_TO_FPxx refactoring ...	commit \| commitdiff \| tree
2025-07-01	Sigbjørn Skjæret	ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158)	commit \| commitdiff \| tree
2025-07-01	Jeff Bolz	vulkan: Add fusion support for RMS_NORM+MUL (llama...	commit \| commitdiff \| tree
2025-07-01	Aman Gupta	CUDA: add bf16 and f32 support to cublas_mul_mat_batche...	commit \| commitdiff \| tree
2025-07-01	Jeff Bolz	vulkan: handle noncontig in the final case of ggml_vk_g...	commit \| commitdiff \| tree
2025-07-01	Jeff Bolz	vulkan: lock accesses of pinned_memory vector (llama...	commit \| commitdiff \| tree
2025-07-01	Xinpeng Dou	fix async_mode bug (llama/14432)	commit \| commitdiff \| tree
2025-07-01	Jeff Bolz	vulkan: Fix GGML_VULKAN_SHADER_DEBUG_INFO (llama/14427)	commit \| commitdiff \| tree
2025-07-01	Radoslav Gerganov	ggml : add ggml_set_rows (llama/14274)	commit \| commitdiff \| tree
2025-07-01	bandoti	cmake: regen vulkan shaders when shaders-gen sources...	commit \| commitdiff \| tree
2025-07-01	Georgi Gerganov	metal : add special-case mat-vec mul for ne00 == 4...	commit \| commitdiff \| tree
2025-07-01	Georgi Gerganov	metal : batch rows copy in a single threadgroup (llama...	commit \| commitdiff \| tree
2025-07-01	R0CKSTAR	musa: enable fp16 mma (all) and cublas on qy2 (llama...	commit \| commitdiff \| tree
2025-07-01	Aaron Teo	ggml-cpu: enable IBM NNPA Vector Intrinsics (llama...	commit \| commitdiff \| tree
2025-07-01	Sigbjørn Skjæret	ggml : do not output unprintable characters on GGUF...	commit \| commitdiff \| tree
2025-07-01	Anton Mitkov	sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel...	commit \| commitdiff \| tree
2025-07-01	lhez	opencl: ref count `ggml_backend_opencl_context` and...	commit \| commitdiff \| tree
2025-07-01	uvos	CUDA/HIP: optimize mmv paths taken for HIP devices...	commit \| commitdiff \| tree
2025-07-01	Johannes Gäßler	CUDA: mul_mat_v support for batch sizes > 1 (llama...	commit \| commitdiff \| tree
2025-07-01	uvos	HIP: enable vec fattn on RDNA4 (llama/14323)	commit \| commitdiff \| tree
2025-07-01	Aman Gupta	CUDA: add mean operation (llama/14313)	commit \| commitdiff \| tree
2025-07-01	Markus Tavenrath	Add support for VK_EXT_debug_utils to add labels to...	commit \| commitdiff \| tree
2025-07-01	Georgi Gerganov	metal : fix thread-safety (llama/14300)	commit \| commitdiff \| tree
2025-07-01	Acly	ggml-cpu : "align corners" for bilinear upscale/downsca...	commit \| commitdiff \| tree
2025-06-25	Acly	build : fix build with clang-cl on Windows (#1284)	commit \| commitdiff \| tree
2025-06-24	Daniel Bevenius	ggml-quants : rename best_mad to best_error (#1283)	commit \| commitdiff \| tree
2025-06-21	Georgi Gerganov	tests : cleanup old tests (#1282)	commit \| commitdiff \| tree
2025-06-20	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-06-20	Aman Gupta	CUDA: add conv_2d_transpose (llama/14287)	commit \| commitdiff \| tree
2025-06-20	Nicolò Scipione	sycl: add usage of enqueue_functions extension (llama...	commit \| commitdiff \| tree
2025-06-20	Christian Kastner	Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama...	commit \| commitdiff \| tree
2025-06-20	Diego Devesa	cuda : synchronize graph capture and cublas handle...	commit \| commitdiff \| tree
2025-06-20	Georgi Gerganov	ggml : fix repack work size for mul_mat_id (llama/14292)	commit \| commitdiff \| tree
2025-06-20	Charles Xu	ggml: Update KleidiAI to v1.9.0 (llama/14277)	commit \| commitdiff \| tree
2025-06-20	Aman Gupta	CUDA: add conv_2d_dw (llama/14265)	commit \| commitdiff \| tree
next

Packaging of ggml-org/ggml

RSS Atom