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

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

overview / pkg / ggml / sources / ggml / shortlog

2025-06-01	lhez	opencl: mark `mul_mat` `f32f32` as supporting non-conti...	commit \| commitdiff \| tree
2025-06-01	Jeff Bolz	vulkan: use timestamp queries for GGML_VULKAN_PERF...	commit \| commitdiff \| tree
2025-06-01	Akarshan Biswas	SYCL: add gelu_erf kernel (llama/13749)	commit \| commitdiff \| tree
2025-06-01	Xuan-Son Nguyen	ggml : add ggml_repeat_4d (llama/13824)	commit \| commitdiff \| tree
2025-05-31	Kai Pastor	vulkan : Remove unexpected ; (#1253)	commit \| commitdiff \| tree
2025-05-31	Kai Pastor	cmake : Fix broken CMake error messages (#1252)	commit \| commitdiff \| tree
2025-05-30	Radoslav Gerganov	ggml : remove ggml_graph_import and ggml_graph_export...	commit \| commitdiff \| tree
2025-05-30	Radoslav Gerganov	ggml : fix pkg-config include path (#1248)	commit \| commitdiff \| tree
2025-05-29	Christian Kastner	ggml : skip tests, examples incompatible with GGML_BACK...	commit \| commitdiff \| tree
2025-05-29	Daniel Tang	ci : Add Windows (#1249)	commit \| commitdiff \| tree
2025-05-29	Georgi Gerganov	sync : whisper.cpp (#1250)	commit \| commitdiff \| tree
2025-05-29	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2025-05-29	Radoslav Gerganov	ggml : install dynamic backends (#1240)	commit \| commitdiff \| tree
2025-05-28	Daniel Tang	ggml : Print backtrace on uncaught C++ exceptions ...	commit \| commitdiff \| tree
2025-05-27	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2025-05-27	Daniel Bevenius	examples : add --print-confidence option to cli (whispe...	commit \| commitdiff \| tree
2025-05-27	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-05-27	xctan	ggml : riscv: add xtheadvector support (llama/13720)	commit \| commitdiff \| tree
2025-05-27	Christian Kastner	ggml-cpu: x86 feature detection is specific to x86...	commit \| commitdiff \| tree
2025-05-27	Diego Devesa	ggml : allow CUDA graphs when using pipeline parallelis...	commit \| commitdiff \| tree
2025-05-27	Georgi Gerganov	cuda : avoid cuGetErrorString (llama/13791)	commit \| commitdiff \| tree
2025-05-27	Akarshan Biswas	SYCL: Add non contiguous support in RMS_NORM and NORM...	commit \| commitdiff \| tree
2025-05-27	Romain Biessy	sycl: Add more debug prints (llama/13640)	commit \| commitdiff \| tree
2025-05-27	Jeff Bolz	vulkan: mark IM2COL as supporting non-contig (llama...	commit \| commitdiff \| tree
2025-05-27	Bizhao Shi	CANN: Add the basic supports of Flash Attention kernel...	commit \| commitdiff \| tree
2025-05-25	Georgi Gerganov	sync : llama.cpp upstream/latest	commit \| commitdiff \| tree
2025-05-25	Akarshan Biswas	SYCL: revert "sycl: simplify bin_bcast_kernel (#13383...	commit \| commitdiff \| tree
2025-05-25	Diego Devesa	ggml-cpu : set openmp wait time if not set (llama/13758)	commit \| commitdiff \| tree
2025-05-25	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-05-25	Xuan-Son Nguyen	ggml : add ggml_gelu_erf() CUDA kernel (llama/13719)	commit \| commitdiff \| tree
2025-05-25	Johannes Gäßler	CUDA: fix race condition in FA vector kernels (llama...	commit \| commitdiff \| tree
2025-05-25	Chenguang Li	CANN: Support MUL_MAT_ID for q8_0 and q4_0 (llama/13705)	commit \| commitdiff \| tree
2025-05-25	Xuan-Son Nguyen	ggml : fix the order of ggml_unary_op (llama/13718)	commit \| commitdiff \| tree
2025-05-25	Jeff Bolz	vulkan: support CPY from any type to itself (llama...	commit \| commitdiff \| tree
2025-05-25	Jeff Bolz	vulkan: Disable coopmat/coopmat2/bfloat extensions...	commit \| commitdiff \| tree
2025-05-25	Judd	use LOG_WARN to replace `std::cerr` (llama/13657)	commit \| commitdiff \| tree
2025-05-25	Nicolò Scipione	sycl : Remove waits from function calls (llama/13702)	commit \| commitdiff \| tree
2025-05-25	Ewan Crawford	SYCL: Avoid using with SYCL-Graph for unsupported nodes...	commit \| commitdiff \| tree
2025-05-25	Henry Linjamäki	opencl: Add support for multiple devices (llama/12622)	commit \| commitdiff \| tree
2025-05-25	Henry Linjamäki	opencl: fix couple crashes (llama/12795)	commit \| commitdiff \| tree
2025-05-25	Xuan-Son Nguyen	ggml : add ggml_gelu_erf() (llama/13667)	commit \| commitdiff \| tree
2025-05-25	R0CKSTAR	musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn...	commit \| commitdiff \| tree
2025-05-25	Eve	vulkan: fix warnings (llama/13626)	commit \| commitdiff \| tree
2025-05-25	Johannes Gäßler	CUDA: skip fully masked-out KV in FA vec kernel (llama...	commit \| commitdiff \| tree
2025-05-25	Svetlozar Georgiev	sycl: disable reorder for sycl mulmat (llama/13536)	commit \| commitdiff \| tree
2025-05-25	Georgi Gerganov	metal : fix typo in FA kernel comments (llama/13651)	commit \| commitdiff \| tree
2025-05-25	Nicolò Scipione	sycl : Overcoming workaround for mmap() allocation...	commit \| commitdiff \| tree
2025-05-25	0cc4m	Vulkan: Add f32 accumulator support to quantized mul...	commit \| commitdiff \| tree
2025-05-19	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-05-19	Chenguang Li	CANN: Support MOE Model MUL_MAT_ID (llama/13042)	commit \| commitdiff \| tree
2025-05-19	Gilad S.	cmake: use the current build config for vulkan-shaders...	commit \| commitdiff \| tree
2025-05-19	Jeff Bolz	vulkan: move common FA code to flash_attn_base.comp...	commit \| commitdiff \| tree
2025-05-19	Jeff Bolz	vulkan: use scalar FA rather than coopmat2 when N=...	commit \| commitdiff \| tree
2025-05-19	Georgi Gerganov	metal : add FA-vec kernel for head size 64 (llama/13583)	commit \| commitdiff \| tree
2025-05-19	Łukasz Ślusarczyk	sycl : fixed compilation warnings (llama/13582)	commit \| commitdiff \| tree
2025-05-19	Diego Devesa	gguf : use ggml log system (llama/13571)	commit \| commitdiff \| tree
2025-05-19	Atharva Dubey	sycl: simplify bin_bcast_kernel (llama/13383)	commit \| commitdiff \| tree
2025-05-19	Svetlozar Georgiev	sycl: reordered Q4_K MMVQ (llama/13109)	commit \| commitdiff \| tree
2025-05-19	Łukasz Ślusarczyk	sycl: use oneDNN for matrices multiplication (llama...	commit \| commitdiff \| tree
2025-05-19	Yibo Cai	arm64: optimize q6_k_q8_k kernel with i8mm (llama/13519)	commit \| commitdiff \| tree
2025-05-19	Johannes Gäßler	CUDA: fix crash on large batch size for quant. MoE...	commit \| commitdiff \| tree
2025-05-19	Johannes Gäßler	CUDA: faster Deepseek FA, add Turing support (llama...	commit \| commitdiff \| tree
2025-05-19	bandoti	cmake: simplify vulkan shader test logic (llama/13263)	commit \| commitdiff \| tree
2025-05-19	Jeff Bolz	vulkan: KHR_coopmat flash attention (llama/13506)	commit \| commitdiff \| tree
2025-05-19	Jeff Bolz	vulkan: workaround FA compile failures on macos (llama...	commit \| commitdiff \| tree
2025-05-19	Georgi Gerganov	metal : use FA-vec kernel up to batch size 20 (llama...	commit \| commitdiff \| tree
2025-05-19	Georgi Gerganov	metal : optimize multi-sequence FA vec kernel (llama...	commit \| commitdiff \| tree
2025-05-19	Dan Johansson	ggml-cpu: Update KleidiAI to v1.6 and fix include direc...	commit \| commitdiff \| tree
2025-05-19	Johannes Gäßler	mnist: fix segmentation fault (#1227)	commit \| commitdiff \| tree
2025-05-19	Diego Devesa	ggml : fix apple OS check in ggml_print_backtrace ...	commit \| commitdiff \| tree
2025-05-17	Daniel Tang	ggml : Fix missing backtrace on Linux (#1228)	commit \| commitdiff \| tree
2025-05-13	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2025-05-13	Daniel Bevenius	examples : update link to Paul Tol's color scheme ...	commit \| commitdiff \| tree
2025-05-13	Georgi Gerganov	examples : update to ggml-opt and ggml-backend changes...	commit \| commitdiff \| tree
2025-05-13	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-05-13	lhez	opencl: remove unnecessary assert for `add` (llama...	commit \| commitdiff \| tree
2025-05-13	Johannes Gäßler	llama/ggml: add LLM training support (llama/10544)	commit \| commitdiff \| tree
2025-05-13	Dan Johansson	ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel...	commit \| commitdiff \| tree
2025-05-13	Johannes Gäßler	CUDA: fix misaligned synchronization in FA (llama/13469)	commit \| commitdiff \| tree
2025-05-13	Xuan-Son Nguyen	ggml : add mrope kernel for metal (llama/13457)	commit \| commitdiff \| tree
2025-05-13	Atharva Dubey	enable dpcpp nightly builds with libraries (llama/13406)	commit \| commitdiff \| tree
2025-05-13	Johannes Gäßler	CUDA: fix crash with partial offloading of MoE (llama...	commit \| commitdiff \| tree
2025-05-13	David Huang	Add `--no-op-offload` to improve `-ot` pp perf in MoE...	commit \| commitdiff \| tree
2025-05-13	Johannes Gäßler	CUDA: fix race conditions FlashAttention kernels (llama...	commit \| commitdiff \| tree
2025-05-13	Johannes Gäßler	CUDA: fix FlashAttention on Turing (llama/13415)	commit \| commitdiff \| tree
2025-05-13	Jeff Bolz	vulkan: scalar flash attention implementation (llama...	commit \| commitdiff \| tree
2025-05-13	Alberto Cabrera...	sycl : implementation of reordered Q4_0 MMVQ for Intel...	commit \| commitdiff \| tree
2025-05-13	Georgi Gerganov	metal : optimize MoE for large batches (llama/13388)	commit \| commitdiff \| tree
2025-05-13	Johannes Gäßler	CUDA: FA support for Deepseek (Ampere or newer) (llama...	commit \| commitdiff \| tree
2025-05-13	Johannes Gäßler	CUDA: fix crash on large batch size for MoE models...	commit \| commitdiff \| tree
2025-05-13	Radoslav Gerganov	rpc : add rpc_msg_set_tensor_hash_req (llama/13353)	commit \| commitdiff \| tree
2025-05-13	Jeff Bolz	vulkan: Allow up to 4096 elements for mul_mat_id row_id...	commit \| commitdiff \| tree
2025-05-13	Alberto Cabrera...	sycl: addressing non-contiguous src1 mul_mats (nc and...	commit \| commitdiff \| tree
2025-05-08	Taylor	sam : support box prompt (#1206)	commit \| commitdiff \| tree
2025-05-07	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2025-05-07	R0CKSTAR	cuda : remove nrows_x in mul_mat_q_process_tile (llama...	commit \| commitdiff \| tree
2025-05-07	Johannes Gäßler	CUDA: mix virt/real CUDA archs for GGML_NATIVE=OFF...	commit \| commitdiff \| tree
2025-05-07	Akarshan Biswas	SYCL: Disable reorder optimize by default and stop...	commit \| commitdiff \| tree
2025-05-07	Johannes Gäßler	CUDA: fix bad asserts for partial offload (llama/13337)	commit \| commitdiff \| tree
2025-05-07	Johannes Gäßler	CUDA: fix --split-mode row for MMQ (llama/13323)	commit \| commitdiff \| tree
next

Packaging of ggml-org/ggml

RSS Atom