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

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

overview / pkg / ggml / sources / ggml / shortlog

2024-03-27	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-03-27	Georgi Gerganov	whisper : improve handling of prompts (whisper/1981)	commit \| commitdiff \| tree
2024-03-27	Sanchit Gandhi	whisper : improve support for distil-large-v3 (whisper...	commit \| commitdiff \| tree
2024-03-27	denersc	whisper : token-level timestamps with DTW (whisper...	commit \| commitdiff \| tree
2024-03-27	Jo Liss	examples : rename --audio-context to --audio-ctx per...	commit \| commitdiff \| tree
2024-03-27	Georgi Gerganov	examples : more CUDA leftovers (#0)	commit \| commitdiff \| tree
2024-03-27	Georgi Gerganov	examples : fix CUBLAS leftovers (#0)	commit \| commitdiff \| tree
2024-03-27	Georgi Gerganov	sync : adapt to CUDA changes (#0)	commit \| commitdiff \| tree
2024-03-27	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-03-27	AidanBeltonS	Fix batched impl for NVidia GPU (llama/6164)	commit \| commitdiff \| tree
2024-03-27	Kawrakow	Make IQ1_M work for QK_K = 64 (llama/6327)	commit \| commitdiff \| tree
2024-03-27	compilade	llama : greatly reduce output buffer memory usage ...	commit \| commitdiff \| tree
2024-03-27	Kawrakow	IQ1_M: 1.75 bpw quantization (llama/6302)	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : rename build flag to LLAMA_CUDA (llama/6299)	commit \| commitdiff \| tree
2024-03-27	Kawrakow	tests : include IQ2_XXS and IQ2_XS in test-quantize...	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : refactor into multiple files (llama/6269)	commit \| commitdiff \| tree
2024-03-27	Justine Tunney	ggml : support AVX512VNNI (llama/6280)	commit \| commitdiff \| tree
2024-03-27	Rick G	Fix heap corruption from wmode out-of-bound writes...	commit \| commitdiff \| tree
2024-03-27	Meng, Hengyu	offload op (llama/6217)	commit \| commitdiff \| tree
2024-03-27	Jared Van Bortel	use _wfopen instead of fopen on Windows (llama/6248)	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : add LLAMA_CUDA_NO_PEER_COPY to workaround broken...	commit \| commitdiff \| tree
2024-03-27	Georgi Gerganov	metal : proper assert for mat-mat memory alignment...	commit \| commitdiff \| tree
2024-03-27	Georgi Gerganov	metal : pad n_ctx by 32 (llama/6177)	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : disable host register by default (llama/6206)	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : fix LLAMA_CUDA_F16 build (llama/6197)	commit \| commitdiff \| tree
2024-03-27	Kawrakow	ggml : same IQ4_NL quantization for CPU/CUDA/Metal...	commit \| commitdiff \| tree
2024-03-27	Kawrakow	Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized...	commit \| commitdiff \| tree
2024-03-27	AidanBeltonS	Add nvidia and amd backends (llama/6157)	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : fix conflict with std::swap (llama/6186)	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : print the returned error when CUDA initializatio...	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : refactor to remove global resources (llama/6170)	commit \| commitdiff \| tree
2024-03-27	Abhilash Majumder	increase igpu cluster limit (llama/6159)	commit \| commitdiff \| tree
2024-03-27	slaren	backend : set max split inputs to GGML_MAX_SRC (llama...	commit \| commitdiff \| tree
2024-03-27	slaren	backend : offload large batches to GPU (llama/6083)	commit \| commitdiff \| tree
2024-03-27	GainLee	ggml:fix finding transfer queue family index error...	commit \| commitdiff \| tree
2024-03-27	AmirAli Mirian	ggml : add AVX512F SIMD (llama/6088)	commit \| commitdiff \| tree
2024-03-27	slaren	cuda : disable unused cudaLaunchHostFunc code (llama...	commit \| commitdiff \| tree
2024-03-27	Neo Zhang Jianyu	fix set main gpu error (llama/6073)	commit \| commitdiff \| tree
2024-03-27	AidanBeltonS	Fix non-intel device selection (llama/6042)	commit \| commitdiff \| tree
2024-03-27	Ondřej Čertík	gguf : add support for I64 and F64 arrays (llama/6062)	commit \| commitdiff \| tree
2024-03-22	Bryan Lozano	cmake : bump to 3.12 (#768)	commit \| commitdiff \| tree
2024-03-22	Bryan Lozano	examples : fix simple (#770)	commit \| commitdiff \| tree
2024-03-18	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-03-18	Georgi Gerganov	whisper : set outputs from conv graph (whisper/1959)	commit \| commitdiff \| tree
2024-03-18	slaren	alloc : fix allocation data of pre-allocated leafs	commit \| commitdiff \| tree
2024-03-15	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-03-15	Georgi Gerganov	spec : add GGUF diagram (#765)	commit \| commitdiff \| tree
2024-03-14	slaren	update examples and tests	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : add ggml-common.h	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : designate enum vals for integer types (llama...	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	metal : build metallib + fix embed path (llama/6015)	commit \| commitdiff \| tree
2024-03-14	slaren	llama : add pipeline parallelism support (llama/6017)	commit \| commitdiff \| tree
2024-03-14	slaren	test-backend-ops : skip CPU backend by default (llama...	commit \| commitdiff \| tree
2024-03-14	AidanBeltonS	Update get version (llama/6025)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : reuse quantum structs across backends (llama...	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : fix UB in IQ2_S and IQ3_S (llama/6012)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	sycl : update IQ1_S kernels (WIP - not working!) (llama...	commit \| commitdiff \| tree
2024-03-14	Kawrakow	1.5 bit: we can do even better (llama/5999)	commit \| commitdiff \| tree
2024-03-14	Michael Podvitskiy	ggml, ci : Windows ARM runner and build fixes (llama...	commit \| commitdiff \| tree
2024-03-14	Kawrakow	Better 1.5 bit quantization (llama/5971)	commit \| commitdiff \| tree
2024-03-14	Abhilash Majumder	Add q3_s and q1_s (llama/5886)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	metal : move mm_id indices to shared mem (llama/5982)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : remove __constant__ specifier for CUDA tables...	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla...	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : remove old quantization functions (llama/5942)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : add ggml-common.h to deduplicate shared code...	commit \| commitdiff \| tree
2024-03-14	compilade	llama : support Mamba Selective State Space Models...	commit \| commitdiff \| tree
2024-03-13	compilade	gguf : add Mamba keys and tensors (#763)	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-03-10	Josh Bleecher...	whisper : document whisper_batch.n_seq_id (whisper...	commit \| commitdiff \| tree
2024-03-10	Josh Bleecher...	whisper : improve beam search candidate diversity ...	commit \| commitdiff \| tree
2024-03-10	Josh Bleecher...	whisper : make beam candidate sort more stable (whisper...	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	ggml : try fix 32-bit arm compat (whisper/1938)	commit \| commitdiff \| tree
2024-03-08	Georgi Gerganov	sync : whisper.cpp	commit \| commitdiff \| tree
2024-03-08	F1L1P	examples : Auto lowercase language parameter in main...	commit \| commitdiff \| tree
2024-03-08	zhouwg	whisper : fix typo (whisper/1925)	commit \| commitdiff \| tree
2024-03-08	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-03-08	Neo Zhang Jianyu	Revert "[SYCL] fix error when set main gpu to non-zero...	commit \| commitdiff \| tree
2024-03-08	Neo Zhang Jianyu	fix error when set main gpu to non-zero (llama/5901)	commit \| commitdiff \| tree
2024-03-08	Jared Van Bortel	ggml : use SYS_get_cpu if SYS_getcpu is not defined...	commit \| commitdiff \| tree
2024-03-08	bobqianic	ggml : use `uint8x16_t` return type for `ggml_vqtbl1q_u...	commit \| commitdiff \| tree
2024-03-08	Neo Zhang Jianyu	add wait() to make code stable (llama/5895)	commit \| commitdiff \| tree
2024-03-08	Jared Van Bortel	quants : use MM256_SET_M128I consistently to fix gcc...	commit \| commitdiff \| tree
2024-03-08	0cc4m	Vulkan Improvements (llama/5835)	commit \| commitdiff \| tree
2024-03-08	Neo Zhang Jianyu	fix mul_mat fault in CI/unit-test (llama/5862)	commit \| commitdiff \| tree
2024-03-08	Georgi Gerganov	ggml : fix unknown status (llama/0)	commit \| commitdiff \| tree
2024-03-07	slaren	magika : fix ggml_backend_graph_compute status check...	commit \| commitdiff \| tree
2024-03-05	Georgi Gerganov	whisper : fix compute helper return (#750)	commit \| commitdiff \| tree
2024-03-04	Michael Podvitskiy	ggml : introduce ggml_status (#750)	commit \| commitdiff \| tree
2024-03-04	Georgi Gerganov	sync : llama.cpp	commit \| commitdiff \| tree
2024-03-04	slaren	cuda : fix data race in soft max (llama/5853)	commit \| commitdiff \| tree
2024-03-04	Georgi Gerganov	ggml : fix IQ3_S AVX implementation (llama/5834)	commit \| commitdiff \| tree
2024-03-04	Kawrakow	ggml : IQ3_S improvements (llama/5829)	commit \| commitdiff \| tree
2024-03-04	Neo Zhang Jianyu	Support multiple GPUs (split mode) on SYCL backend...	commit \| commitdiff \| tree
2024-03-04	ddpasa	ggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was...	commit \| commitdiff \| tree
2024-03-04	AidanBeltonS	Use batched mul_mat pathway (llama/5591)	commit \| commitdiff \| tree
2024-03-04	Eve	make portability_enumeration_ext apple only (llama...	commit \| commitdiff \| tree
2024-03-03	leejet	add some new ops, fix some operators and add batch...	commit \| commitdiff \| tree
2024-02-28	Steward Garcia	ggml : add simple example (#713)	commit \| commitdiff \| tree
next

Packaging of ggml-org/ggml

RSS Atom