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

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

overview / pkg / ggml / sources / llama.cpp / shortlog

2024-08-12	Nico Bosshard	llama : model-based max number of graph nodes calculati...	commit \| commitdiff \| tree
2024-08-12	Frank Mai	docs: introduce gpustack and gguf-parser (#8873)	commit \| commitdiff \| tree
2024-08-12	DavidKorczynski	grammar-parser : fix possible null-deref (#9004)	commit \| commitdiff \| tree
2024-08-12	DavidKorczynski	ggml: fix div-by-zero (#9003)	commit \| commitdiff \| tree
2024-08-12	Liu Jia	Fix a spelling mistake (#9001)	commit \| commitdiff \| tree
2024-08-12	Georgi Gerganov	py : fix requirements check '==' -> '~=' (#8982)	commit \| commitdiff \| tree
2024-08-12	Georgi Gerganov	server : handle models with missing EOS token (#8997)	commit \| commitdiff \| tree
2024-08-11	compilade	gguf-py : Numpy dequantization for most types (#8939)	commit \| commitdiff \| tree
2024-08-11	Georgi Gerganov	flake.lock: Update (#8979)	commit \| commitdiff \| tree
2024-08-11	Neo Zhang	update guide (#8909)	commit \| commitdiff \| tree
2024-08-11	fairydreaming	llama : check all graph nodes when searching for result...	commit \| commitdiff \| tree
2024-08-11	Markus Tavenrath	Optimize Vulkan backend for better CPU performance...	commit \| commitdiff \| tree
2024-08-10	slaren	metal : fix uninitialized abort_callback (#8968)	commit \| commitdiff \| tree
2024-08-10	Xuan Son Nguyen	llama : default n_swa for phi-3 (#8931)	commit \| commitdiff \| tree
2024-08-10	fairydreaming	Add support for encoder-only T5 models (#8900)	commit \| commitdiff \| tree
2024-08-10	Matteo Mortari	gguf-py : fix double call to add_architecture() (#8952)	commit \| commitdiff \| tree
2024-08-09	Georgi Gerganov	Merge commit from fork	commit \| commitdiff \| tree
2024-08-09	fairydreaming	llama : add support for lora adapters in T5 model ...	commit \| commitdiff \| tree
2024-08-09	Georgi Gerganov	make : fix llava obj file race (#8946)	commit \| commitdiff \| tree
2024-08-09	Georgi Gerganov	llama : better replace_all (cont) (#8926)	commit \| commitdiff \| tree
2024-08-09	tc-mb	llava : support MiniCPM-V-2.5 (#7599)	commit \| commitdiff \| tree
2024-08-09	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-08-09	Matt Stephenson	whisper : use vulkan as gpu backend when available...	commit \| commitdiff \| tree
2024-08-09	Daniel Bevenius	embedding : add --pooling option to README.md [no ci...	commit \| commitdiff \| tree
2024-08-09	Daniel Bevenius	llama : fix typo in llama_tensor_get_type comment ...	commit \| commitdiff \| tree
2024-08-09	Mathieu Geli	server : add one level list nesting for embeddings...	commit \| commitdiff \| tree
2024-08-09	compilade	llama : reduce useless copies when saving session ...	commit \| commitdiff \| tree
2024-08-08	compilade	gguf-py : simplify support for quant types (#8838)	commit \| commitdiff \| tree
2024-08-08	Georgi Gerganov	scripts : sync cann files (#0)	commit \| commitdiff \| tree
2024-08-08	Georgi Gerganov	scripts : fix sync filenames (#0)	commit \| commitdiff \| tree
2024-08-08	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-08-08	Borislav Stanimirov	ggml : ignore more msvc warnings (ggml/906)	commit \| commitdiff \| tree
2024-08-08	Georgi Gerganov	metal : fix struct name (ggml/912)	commit \| commitdiff \| tree
2024-08-08	Conrad Kramer	metal : add abort callback (ggml/905)	commit \| commitdiff \| tree
2024-08-08	Pablo Duboue	make : clean llamafile objects (#8923)	commit \| commitdiff \| tree
2024-08-07	slaren	make : use C compiler to build metal embed object ...	commit \| commitdiff \| tree
2024-08-07	slaren	ggml-backend : fix async copy from CPU (#8897)	commit \| commitdiff \| tree
2024-08-07	Ouadie EL FAROUKI	[SYCL] Updated SYCL device filtering (#8901)	commit \| commitdiff \| tree
2024-08-07	Johannes Gäßler	CUDA/HIP: fix tests/test-backend-ops (#8896)	commit \| commitdiff \| tree
2024-08-07	Zhenwei Jin	llama-bench : add support for getting cpu info on Windo...	commit \| commitdiff \| tree
2024-08-06	Daniel Bevenius	quantize : update usage comment in quantize.cpp (#8889)	commit \| commitdiff \| tree
2024-08-06	Nexes the Old	typo correction (#8891)	commit \| commitdiff \| tree
2024-08-06	Xuan Son Nguyen	server : add lora hotswap endpoint (WIP) (#8857)	commit \| commitdiff \| tree
2024-08-06	Johannes Gäßler	CUDA: fix padding logic for FP16/FP32 (#8884)	commit \| commitdiff \| tree
2024-08-06	Daniel Bevenius	simple : update name of executable to llama-simple...	commit \| commitdiff \| tree
2024-08-06	Jaeden Amero	cmake : Link vulkan-shaders-gen with pthreads (#8835)	commit \| commitdiff \| tree
2024-08-06	MaggotHATE	[Vulkan] Fix compilation of `vulkan-shaders-gen` on...	commit \| commitdiff \| tree
2024-08-06	Georgi Gerganov	contributing : add note about write access	commit \| commitdiff \| tree
2024-08-06	Molly Sophia	ggml : add epsilon as a parameter for group_norm (...	commit \| commitdiff \| tree
2024-08-06	Douglas Hanley	convert : add support for XLMRoberta embedding models...	commit \| commitdiff \| tree
2024-08-06	Mengqing Cao	[CANN]: Fix ggml_backend_cann_buffer_get_tensor (#8871)	commit \| commitdiff \| tree
2024-08-06	Neo Zhang	[SYCL] correct cmd name (#8877)	commit \| commitdiff \| tree
2024-08-05	Liu Jia	common : Changed tuple to struct (TODO fix) (#8823)	commit \| commitdiff \| tree
2024-08-05	wangshuai09	cann: fix buffer_num and runtime speed slowly error...	commit \| commitdiff \| tree
2024-08-05	Eric Curtin	readme : add ramalama to the availables UI (#8811)	commit \| commitdiff \| tree
2024-08-05	Justine Tunney	ggml : fix overflows in elu function (#8866)	commit \| commitdiff \| tree
2024-08-05	Brian	py: Add more authorship metadata from model card (...	commit \| commitdiff \| tree
2024-08-05	fairydreaming	Stop the generation when <\|eom_id\|> token is encountere...	commit \| commitdiff \| tree
2024-08-05	stduhpf	cmake: fix paths for vulkan shaders compilation on...	commit \| commitdiff \| tree
2024-08-05	BarfingLemurs	readme : update model list (#8851)	commit \| commitdiff \| tree
2024-08-05	Georgi Gerganov	llama : better replace_all (#8852)	commit \| commitdiff \| tree
2024-08-05	0cc4m	vulkan : fix Qantized Mat-Vec Mul on AMD GPUs for ncols...	commit \| commitdiff \| tree
2024-08-05	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-08-05	0cc4m	vulkan : implement Stable Diffusion operators (ggml...	commit \| commitdiff \| tree
2024-08-05	Daniel Bevenius	ggml : move c parameter comment to ggml_rope_ext (ggml...	commit \| commitdiff \| tree
2024-08-05	wangshuai09	cann: support q4_0 model (#8822)	commit \| commitdiff \| tree
2024-08-04	Brandon Squizzato	Install curl in runtime layer (#8693)	commit \| commitdiff \| tree
2024-08-04	ardfork	Server: Don't ignore llama.cpp params (#8754)	commit \| commitdiff \| tree
2024-08-04	Brian Cunnie	batched-bench : handle empty `-npl` (#8839)	commit \| commitdiff \| tree
2024-08-04	Daniel Bevenius	baby-llama : remove duplicate vector include	commit \| commitdiff \| tree
2024-08-04	Georgi Gerganov	flake.lock: Update (#8847)	commit \| commitdiff \| tree
2024-08-03	jdomke	ggml : reading the runtime sve config of the cpu (...	commit \| commitdiff \| tree
2024-08-02	Sigbjørn Skjæret	Fix conversion of unnormalized BF16->BF16 weights ...	commit \| commitdiff \| tree
2024-08-02	Mengqing Cao	cann: Fix ggml_cann_im2col for 1D im2col (#8819)	commit \| commitdiff \| tree
2024-08-02	Ouadie EL FAROUKI	[SYCL] Fixing wrong VDR iq4nl value (#8812)	commit \| commitdiff \| tree
2024-08-01	matteo	ggml-cuda: Adding support for unified memory (#8035)	commit \| commitdiff \| tree
2024-08-01	Alex O'Connell	Build: Only include execinfo.h on linux systems that...	commit \| commitdiff \| tree
2024-08-01	slaren	cuda : fix dmmv cols requirement to 2*GGML_CUDA_DMMV_X...	commit \| commitdiff \| tree
2024-08-01	wangshuai09	cann: support q8_0 for Ascend\b backend (#8805)	commit \| commitdiff \| tree
2024-07-31	Igor Okulist	server : update llama-server embedding flag documentati...	commit \| commitdiff \| tree
2024-07-31	Clint Herron	Build: Fix potential race condition (#8781)	commit \| commitdiff \| tree
2024-07-31	pculliton	Adding Gemma 2 2B configs (#8784)	commit \| commitdiff \| tree
2024-07-31	Borislav Stanimirov	cmake : fix use of external ggml (#8787)	commit \| commitdiff \| tree
2024-07-30	Someone	nix: cuda: rely on propagatedBuildInputs (#8772)	commit \| commitdiff \| tree
2024-07-30	Brian	py: add_array() will not add to kv store if value is...	commit \| commitdiff \| tree
2024-07-30	l3utterfly	added android implementation of ggml_print_backtrace_sy...	commit \| commitdiff \| tree
2024-07-30	Georgi Gerganov	flake.lock: Update (#8729)	commit \| commitdiff \| tree
2024-07-30	wangshuai09	cann: update cmake (#8765)	commit \| commitdiff \| tree
2024-07-30	zhentaoyu	[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)	commit \| commitdiff \| tree
2024-07-29	CarterLi999	ggml: bugfix: fix the inactive elements is agnostic...	commit \| commitdiff \| tree
2024-07-29	R0CKSTAR	cuda : organize vendor-specific headers into vendors...	commit \| commitdiff \| tree
2024-07-29	Meng, Hengyu	[SYCL] add conv support (#8688)	commit \| commitdiff \| tree
2024-07-28	Johannes Gäßler	cmake: use 1 more thread for non-ggml in CI (#8740)	commit \| commitdiff \| tree
2024-07-28	Austin	chore : Fix vulkan related compiler warnings, add help...	commit \| commitdiff \| tree
2024-07-28	compilade	llama : refactor session file management (#8699)	commit \| commitdiff \| tree
2024-07-27	R0CKSTAR	feat: Support Moore Threads GPU (#8383)	commit \| commitdiff \| tree
2024-07-27	Georgi Gerganov	scripts : sync vulkan-shaders (#0)	commit \| commitdiff \| tree
2024-07-27	Georgi Gerganov	scripts : sync ggml-aarch64 sources	commit \| commitdiff \| tree
2024-07-27	Georgi Gerganov	ggml : add missing semicolon (#0)	commit \| commitdiff \| tree
2024-07-27	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom