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

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

overview / pkg / ggml / sources / ggml / shortlog

2024-11-15	Georgi Gerganov	sync : leftovers (#0)	commit \| commitdiff \| tree
2024-11-15	Georgi Gerganov	test-dup : minor fix	commit \| commitdiff \| tree
2024-11-15	Georgi Gerganov	cmake : restore CMakeLists.txt (llama/10256)	commit \| commitdiff \| tree
2024-11-15	Eve	AVX BF16 and single scale quant optimizations (llama...	commit \| commitdiff \| tree
2024-11-15	Romain Biessy	sycl: Use syclcompat::dp4a (llama/10267)	commit \| commitdiff \| tree
2024-11-15	Charles Xu	backend cpu: add online flow for aarch64 Q4_0 GEMV...	commit \| commitdiff \| tree
2024-11-15	Diego Devesa	ggml : build backends as libraries (llama/10256)	commit \| commitdiff \| tree
2024-11-15	Georgi Gerganov	scripts : update sync llama.cpp	commit \| commitdiff \| tree
2024-11-15	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-11-15	Georgi Gerganov	cmake : fix ppc64 check (whisper/0)	commit \| commitdiff \| tree
2024-11-15	thewh1teagle	ggml : vulkan logs (whisper/2547)	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-11-13	Alberto Cabrera...	sycl : Fixes to broken builds and test-backend-ops...	commit \| commitdiff \| tree
2024-11-13	Jeff Bolz	vulkan: Optimize contiguous copies (llama/10254)	commit \| commitdiff \| tree
2024-11-13	Jeff Bolz	vulkan: Throttle the number of shader compiles during...	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : more precise Q*K in FA vec kernel (llama/10247)	commit \| commitdiff \| tree
2024-11-13	Jeff Bolz	vulkan: Fix newly added tests for permuted mul_mat...	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : reorder write loop in mul mat kernel + style...	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : fix build and some more comments (llama/10229)	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : fix F32 accumulation in FA vec kernel (llama...	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : hide debug messages from normal log	commit \| commitdiff \| tree
2024-11-13	SXX	ggml: fix zero division in ‘dne’ calculation in CUDA...	commit \| commitdiff \| tree
2024-11-13	amritahs-ibm	ggml : optimize llamafile cpu matrix multiplication...	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : opt-in compile flag for BF16 (llama/10218)	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : improve clarity (minor) (llama/10171)	commit \| commitdiff \| tree
2024-11-13	Georgi Gerganov	metal : optimize FA kernels (llama/10171)	commit \| commitdiff \| tree
2024-11-08	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-11-08	Diego Devesa	ggml : add ggml-cpu.h to the public headers (llama...	commit \| commitdiff \| tree
2024-11-08	snadampal	fix q4_0_8_8 format for corrupted tokens issue (llama...	commit \| commitdiff \| tree
2024-11-08	Zhiyuan Li	Optimize RWKV6 Operator Naming and Implement Multi...	commit \| commitdiff \| tree
2024-11-08	Georgi Gerganov	metal : add BF16 support (llama/8439)	commit \| commitdiff \| tree
2024-11-08	Diego Devesa	metal : fix from ptr buffer name (llama/10189)	commit \| commitdiff \| tree
2024-11-08	Georgi Gerganov	ggml : adjust is_first_call init value (llama/10193)	commit \| commitdiff \| tree
2024-11-08	Georgi Gerganov	metal : add quantized FA support (llama/10149)	commit \| commitdiff \| tree
2024-11-08	Diego Devesa	ggml : fix arch check in bf16_to_fp32 (llama/10164)	commit \| commitdiff \| tree
2024-11-08	Eve	Q6_K AVX improvements (llama/10118)	commit \| commitdiff \| tree
2024-11-04	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	ggml : fix gelu tables initialization (llama/10172)	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	ggml : fix q4xx mat mul, increase ggml_aligned_malloc...	commit \| commitdiff \| tree
2024-11-04	snadampal	fix build break on arm64 linux (llama/10166)	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	cuda : clear error after changing peer access (llama...	commit \| commitdiff \| tree
2024-11-04	Georgi Gerganov	metal : simplify f16 and f32 dequant kernels (llama/0)	commit \| commitdiff \| tree
2024-11-04	Georgi Gerganov	metal : move dequantize templates to beginning of MSL...	commit \| commitdiff \| tree
2024-11-04	leo-pony	CANN: adjust backend registry refactor. (llama/10158)	commit \| commitdiff \| tree
2024-11-04	slaren	update tests and examples	commit \| commitdiff \| tree
2024-11-04	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	ggml : move CPU backend to a separate file (llama/10144)	commit \| commitdiff \| tree
2024-11-04	Georgi Gerganov	metal : minor fixup in FA kernel (llama/10143)	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	llama : add simple-chat example (llama/10124)	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	llama : use smart pointers for ggml resources (llama...	commit \| commitdiff \| tree
2024-11-04	Shupei Fan	vulkan : improve ggml_vk_create_buffer error handling...	commit \| commitdiff \| tree
2024-11-04	Georgi Gerganov	ggml : remove ggml_scratch (llama/10121)	commit \| commitdiff \| tree
2024-11-04	Zhenwei Jin	build: fix build error in Windows env with OneAPI setup...	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	llama : fix buffer checks for mamba and rwk (llama...	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	ggml : check tensor name lengths in gguf files (llama...	commit \| commitdiff \| tree
2024-11-04	Sergio López	kompute: add mul_mat_q4_k shader (llama/10097)	commit \| commitdiff \| tree
2024-11-04	Sergio López	kompute: add backend registry / device interfaces ...	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	ggml : fix memory leaks when loading invalid gguf files...	commit \| commitdiff \| tree
2024-11-04	xctan	ggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (llama...	commit \| commitdiff \| tree
2024-11-04	Diego Devesa	llama : refactor model loader with backend registry...	commit \| commitdiff \| tree
2024-11-04	Changyeon Kim	ggml: Add POOL2D OP for GPU acceleration to the Vulkan...	commit \| commitdiff \| tree
2024-11-04	R0CKSTAR	musa: workaround for Guilty Lockup in cleaning src0...	commit \| commitdiff \| tree
2024-11-04	Georgi Gerganov	scripts : update sync	commit \| commitdiff \| tree
2024-11-02	Yuri Khrustalev	cmake : make it possible linking ggml as external lib...	commit \| commitdiff \| tree
2024-11-01	Plamen Minev	metal : fix minor string leaks (#1004)	commit \| commitdiff \| tree
2024-11-01	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-11-01	Georgi Gerganov	ggml : alloc ggml_contexts on the heap (whisper/2525)	commit \| commitdiff \| tree
2024-10-26	Georgi Gerganov	ggml : remove sync artifacts	commit \| commitdiff \| tree
2024-10-26	Ma Mingfei	ggml : add AMX backend (llama/8998)	commit \| commitdiff \| tree
2024-10-26	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-10-26	Georgi Gerganov	metal : support permuted matrix multiplicaions (llama...	commit \| commitdiff \| tree
2024-10-26	Johannes Gäßler	CUDA: fix insufficient buffer clearing for MMQ (llama...	commit \| commitdiff \| tree
2024-10-26	Johannes Gäßler	CUDA: fix MMQ for non-contiguous src0, add tests (llama...	commit \| commitdiff \| tree
2024-10-26	Georgi Gerganov	scripts : fix sync scripts (amx)	commit \| commitdiff \| tree
2024-10-23	bssrdf	increase cuda_cpy block size (#996)	commit \| commitdiff \| tree
2024-10-23	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-10-23	Jun Hee Yoo	metal : add POOL2D and fix IM2COL (llama/9943)	commit \| commitdiff \| tree
2024-10-23	leo-pony	Adapt to dynamically loadable backends mechanism (llama...	commit \| commitdiff \| tree
2024-10-23	Georgi Gerganov	ggml : add asserts for type conversion in fattn kernels...	commit \| commitdiff \| tree
2024-10-23	Radoslav Gerganov	rpc : pack only RPC structs (llama/9959)	commit \| commitdiff \| tree
2024-10-23	Neo Zhang Jianyu	fix mul_mat_vec_q and *_vec_q error (llama/9939)	commit \| commitdiff \| tree
2024-10-23	Radoslav Gerganov	rpc : backend refactoring (llama/9912)	commit \| commitdiff \| tree
2024-10-23	Ouadie EL FAROUKI	Add SYCL Backend registry, device and Event Interfaces...	commit \| commitdiff \| tree
2024-10-23	Ma Mingfei	add amx kernel for gemm (llama/8998)	commit \| commitdiff \| tree
2024-10-23	Diego Devesa	vulkan : add backend registry / device interfaces ...	commit \| commitdiff \| tree
2024-10-23	Gilad S	fix: allocating CPU buffer with size `0` (llama/9917)	commit \| commitdiff \| tree
2024-10-23	Gilad S	fix: use `vm_allocate` to allocate CPU backend buffer...	commit \| commitdiff \| tree
2024-10-18	Johannes Gäßler	CUDA: fix 1D im2col, add tests (#993)	commit \| commitdiff \| tree
2024-10-16	Daniel Bevenius	ggml : remove redundant set of contexts used field...	commit \| commitdiff \| tree
2024-10-16	Georgi Gerganov	tests : update type traits call (#0)	commit \| commitdiff \| tree
2024-10-16	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-10-16	leo-pony	Fix cann compilation error (llama/9891)	commit \| commitdiff \| tree
2024-10-16	agray3	Vectorize load instructions in dmmv f16 CUDA kernel...	commit \| commitdiff \| tree
2024-10-16	Diego Devesa	ggml : move more prints to the ggml log system (llama...	commit \| commitdiff \| tree
2024-10-16	Diego Devesa	rpc : add backend registry / device interfaces (llama...	commit \| commitdiff \| tree
2024-10-16	R0CKSTAR	musa: add docker image support (llama/9685)	commit \| commitdiff \| tree
2024-10-16	Diego Devesa	ggml : fix BLAS with unsupported types (llama/9775)	commit \| commitdiff \| tree
2024-10-16	Diego Devesa	ggml : add backend registry / device interfaces to...	commit \| commitdiff \| tree
2024-10-16	Andrew Minh...	Update building for Android (llama/9672)	commit \| commitdiff \| tree
2024-10-16	Georgi Gerganov	ggml : add metal backend registry / device (llama/9713)	commit \| commitdiff \| tree
next

Packaging of ggml-org/ggml

RSS Atom