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

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

overview / pkg / ggml / sources / ggml / shortlog

2025-01-29	Nicolò Scipione	SYCL: Introducing memory host pool (llama/11251)	commit \| commitdiff \| tree
2025-01-29	Georgi Gerganov	cmake : add sanitizer flags for llama.cpp (llama/11279)	commit \| commitdiff \| tree
2025-01-29	Jeff Bolz	vulkan: fix coopmat2 flash attention for non-contiguous...	commit \| commitdiff \| tree
2025-01-29	Radoslav Gerganov	rpc : early register backend devices (llama/11262)	commit \| commitdiff \| tree
2025-01-29	Jeff Bolz	vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1...	commit \| commitdiff \| tree
2025-01-29	Jeff Bolz	vulkan: optimize coopmat2 q4_k/q5_k dequant functions...	commit \| commitdiff \| tree
2025-01-29	Jeff Bolz	vulkan: optimize coopmat2 q2_k dequant function (llama...	commit \| commitdiff \| tree
2025-01-29	Johannes Gäßler	CUDA: backwards pass for misc. ops, add tests (llama...	commit \| commitdiff \| tree
2025-01-29	fj-y-saito	ggml: aarch64: implement SVE kernels for q4_K_q8_K...	commit \| commitdiff \| tree
2025-01-29	Eve	vulkan: scale caching for k quants + misc fixes (llama...	commit \| commitdiff \| tree
2025-01-29	Junil Kim	fix: ggml: fix vulkan-shaders-gen build (llama/10448)	commit \| commitdiff \| tree
2025-01-29	Johannes Gäßler	RoPE: fix back, CUDA support for back + noncont. (llama...	commit \| commitdiff \| tree
2025-01-29	Akarshan Biswas	SYCL: Add gated linear attention kernel (llama/11175)	commit \| commitdiff \| tree
2025-01-25	Andrii Ryzhkov	cmake : fix build tests on arm (#1084)	commit \| commitdiff \| tree
2025-01-23	William Tambellini	ggml : add option to not print stack on abort (#1081)	commit \| commitdiff \| tree
2025-01-17	issixx	ggml-cpu : fix ggml_graph_compute_thread did not termin...	commit \| commitdiff \| tree
2025-01-14	Georgi Gerganov	sync : whisper.cpp upstream/0.0.1642	commit \| commitdiff \| tree
2025-01-14	Georgi Gerganov	scripts : sync gguf (cont)	commit \| commitdiff \| tree
2025-01-14	Johannes Gäßler	GGUF: C++ refactor, backend support, misc fixes (skip...	commit \| commitdiff \| tree
2025-01-14	Georgi Gerganov	scripts : sync gguf	commit \| commitdiff \| tree
2025-01-14	lhez	ggml : add opencl backend (skip) (llama/10693)	commit \| commitdiff \| tree
2025-01-14	Georgi Gerganov	scripts : sync opencl	commit \| commitdiff \| tree
2025-01-14	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-01-14	Andreas Kieslinger	cuda : CUDA Graph Compute Function Refactor (precursor...	commit \| commitdiff \| tree
2025-01-14	Radoslav Gerganov	ggml : do not define GGML_USE_CUDA when building with...	commit \| commitdiff \| tree
2025-01-14	0cc4m	Vulkan: Fix float16 use on devices without float16...	commit \| commitdiff \| tree
2025-01-14	Molly Sophia	llama: add support for QRWKV6 model architecture (llama...	commit \| commitdiff \| tree
2025-01-14	Akarshan Biswas	SYCL: Refactor ggml_sycl_compute_forward (llama/11121)	commit \| commitdiff \| tree
2025-01-14	hydai	fix: add missing msg in static_assert (llama/11143)	commit \| commitdiff \| tree
2025-01-14	amritahs-ibm	llamafile : ppc64le MMA INT8 implementation (llama...	commit \| commitdiff \| tree
2025-01-14	Mathieu Baudier	Disable GL_KHR_cooperative_matrix Vulkan extension...	commit \| commitdiff \| tree
2025-01-14	ag2s20150909	fix: Vulkan shader gen binary path when Cross-compiling...	commit \| commitdiff \| tree
2025-01-14	Johannes Gäßler	GGUF: C++ refactor, backend support, misc fixes (llama...	commit \| commitdiff \| tree
2025-01-14	Diego Devesa	ggml-backend : only offload from host buffers (fix...	commit \| commitdiff \| tree
2025-01-14	Diego Devesa	ggml-backend : only offload from host buffers (llama...	commit \| commitdiff \| tree
2025-01-14	Radoslav Gerganov	rpc : code cleanup (llama/11107)	commit \| commitdiff \| tree
2025-01-14	Akarshan Biswas	SYCL: Use get_multi_ptr instead of deprecated get_point...	commit \| commitdiff \| tree
2025-01-14	Johannes Gäßler	CUDA: add BF16 support (llama/11093)	commit \| commitdiff \| tree
2025-01-14	0cc4m	Vulkan: Add device-specific blacklist for coopmat for...	commit \| commitdiff \| tree
2025-01-14	matt23654	Support for models with non-512-aligned tensors over...	commit \| commitdiff \| tree
2025-01-14	Gilad S.	fix: Vulkan shader gen binary path (llama/11037)	commit \| commitdiff \| tree
2025-01-05	Radoslav Gerganov	ggml : allow loading backend with env variable (#1059)	commit \| commitdiff \| tree
2025-01-04	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2025-01-03	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-01-03	Georgi Gerganov	metal : avoid uint (llama/11019)	commit \| commitdiff \| tree
2025-01-03	Srihari-mcw	ggml : fixes for AVXVNNI instruction set with MSVC...	commit \| commitdiff \| tree
2025-01-03	Jeff Bolz	vulkan: optimize mul_mat for small values of N (llama...	commit \| commitdiff \| tree
2025-01-03	Jeff Bolz	vulkan: im2col and matmul optimizations for stable...	commit \| commitdiff \| tree
2025-01-03	Jeff Bolz	vulkan: Use push constant offset to handle misaligned...	commit \| commitdiff \| tree
2025-01-03	Eve	vulkan: multi-row k quants (llama/10846)	commit \| commitdiff \| tree
2025-01-03	Peter	examples, ggml : fix GCC compiler warnings (llama/10983)	commit \| commitdiff \| tree
2025-01-03	Djip007	ggml : more perfo with llamafile tinyblas on x86_64...	commit \| commitdiff \| tree
2025-01-03	Diego Devesa	ggml : use wstring for backend search paths (llama...	commit \| commitdiff \| tree
2025-01-03	Diego Devesa	ggml : fix arm enabled features check (llama/10961)	commit \| commitdiff \| tree
2025-01-03	Diego Devesa	ggml : fix const usage in SSE path (llama/10962)	commit \| commitdiff \| tree
2025-01-03	yuri@FreeBSD	ggml : fix run-time on FreeBSD in get_executable_path...	commit \| commitdiff \| tree
2025-01-03	Jeff Bolz	vulkan: build fixes for 32b (llama/10927)	commit \| commitdiff \| tree
2025-01-03	Jeff Bolz	vulkan: optimize coopmat2 dequant functions (llama...	commit \| commitdiff \| tree
2025-01-03	Adrien Gallouët	ggml-cpu: replace NEON asm with intrinsics in ggml_gemv...	commit \| commitdiff \| tree
2025-01-03	Akarshan Biswas	SYCL: Migrate away from deprecated ggml_tensor->backend...	commit \| commitdiff \| tree
2025-01-03	Diego Devesa	ggml : add test for SVE and disable when it fails ...	commit \| commitdiff \| tree
2025-01-03	Adrien Gallouët	ggml: fix arm build with gcc (llama/10895)	commit \| commitdiff \| tree
2025-01-03	Diego Devesa	ggml : fix arm build (llama/10890)	commit \| commitdiff \| tree
2025-01-03	Georgi Gerganov	tts : add OuteTTS support (llama/10784)	commit \| commitdiff \| tree
2025-01-03	Johannes Gäßler	tests: add tests for GGUF (llama/10830)	commit \| commitdiff \| tree
2024-12-23	Georgi Gerganov	ggml : do not install metal source when embed library...	commit \| commitdiff \| tree
2024-12-19	Daniel Bevenius	ggml : improve inputs log sched_print_assignments ...	commit \| commitdiff \| tree
2024-12-18	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-12-18	Georgi Gerganov	files : remove old sources (#1052)	commit \| commitdiff \| tree
2024-12-17	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-12-17	Georgi Gerganov	ggml : update ggml_backend_cpu_device_supports_op ...	commit \| commitdiff \| tree
2024-12-17	Eve	vulkan: bugfixes for small subgroup size systems +...	commit \| commitdiff \| tree
2024-12-17	Zhiyuan Li	rwkv6: add wkv6 support for Vulkan backend (llama/10829)	commit \| commitdiff \| tree
2024-12-17	HimariO	llama : add Qwen2VL support + multimodal RoPE (llama...	commit \| commitdiff \| tree
2024-12-17	lhez	Introducing experimental OpenCL backend with support...	commit \| commitdiff \| tree
2024-12-17	谢乃闻	Fix crash caused by ggml_backend_load_all when launchin...	commit \| commitdiff \| tree
2024-12-17	Eve	vulkan: small mul_mat_vec optimizations (llama/10665)	commit \| commitdiff \| tree
2024-12-17	Akarshan Biswas	SYCL: Reduce most of the compiler warnings (llama/10748)	commit \| commitdiff \| tree
2024-12-17	Karol Kontny	ggml : Fix compilation issues on ARM platform when...	commit \| commitdiff \| tree
2024-12-17	a3sh	CUDA: faster non-contiguous concat (llama/10760)	commit \| commitdiff \| tree
2024-12-17	Diego Devesa	remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797)	commit \| commitdiff \| tree
2024-12-17	0cc4m	Vulkan: Use improved q4_k and q5_k dequant code in...	commit \| commitdiff \| tree
2024-12-17	0cc4m	Vulkan: Add VK_EXT_subgroup_size_control support to...	commit \| commitdiff \| tree
2024-12-17	Gilad S	ggml: load all backends from a user-provided search...	commit \| commitdiff \| tree
2024-12-17	Jeff Bolz	vulkan: request round-to-even for fp16 in im2col/rope_h...	commit \| commitdiff \| tree
2024-12-17	Eve	vulkan: dynamic subgroup size for the remaining k quant...	commit \| commitdiff \| tree
2024-12-17	Andreas Kieslinger	CUDA: rename macros to avoid conflicts with WinAPI...	commit \| commitdiff \| tree
2024-12-17	Jeff Bolz	vulkan: disable spirv-opt for coopmat shaders (llama...	commit \| commitdiff \| tree
2024-12-17	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-12-17	Georgi Gerganov	cmake : fix "amd64" processor string (whisper/2638)	commit \| commitdiff \| tree
2024-12-17	gn64	vulkan : fix soft_max.comp division by zero (whisper...	commit \| commitdiff \| tree
2024-12-14	Daniel Bevenius	ggml : remove return from ggml_gallocr_allocate_node...	commit \| commitdiff \| tree
2024-12-13	Daniel Bevenius	ggml : add check for grad_accs (#1046)	commit \| commitdiff \| tree
2024-12-10	Georgi Gerganov	common : remove old types	commit \| commitdiff \| tree
2024-12-10	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-12-10	Johannes Gäßler	CUDA: fix shared memory access condition for mmv (llama...	commit \| commitdiff \| tree
2024-12-10	Jeff Bolz	vulkan: fix compile warnings (llama/10731)	commit \| commitdiff \| tree
2024-12-10	stduhpf	Vulkan: fix NaN in tanh.comp with AMD proprietary drive...	commit \| commitdiff \| tree
2024-12-10	Jeff Bolz	vulkan: compile a test shader in cmake to check for...	commit \| commitdiff \| tree
2024-12-10	Georgi Gerganov	ggml : disable iq4_nl interleave size 8 (llama/10709)	commit \| commitdiff \| tree
next

Packaging of ggml-org/ggml

RSS Atom