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

2023-07-25	Kawrakow	Another speed gain for Q4_0 and Q4_1 on Metal (#2375)	commit \| commitdiff \| tree
2023-07-25	Kawrakow	Fix Q4_K and Q5_K for QK_K = 64 on CUDA (#2359)	commit \| commitdiff \| tree
2023-07-25	slaren	server: add rms_norm_eps parameter (#2380)	commit \| commitdiff \| tree
2023-07-25	Henri Vasserman	[Server] Escape HTML in webchat (#2368)	commit \| commitdiff \| tree
2023-07-24	slaren	make rms_norm_eps a parameter (#2374)	commit \| commitdiff \| tree
2023-07-24	Aarni Koskela	Chat UI extras (#2366)	commit \| commitdiff \| tree
2023-07-24	Georgi Gerganov	ggml : sync (unary ops refactor, static-correctness...	commit \| commitdiff \| tree
2023-07-24	Kawrakow	Fix scalar version of Q5_K when QK_K = 64 (#2362)	commit \| commitdiff \| tree
2023-07-24	Evan Jones	llama : add grammar-based sampling (#1773)	commit \| commitdiff \| tree
2023-07-23	Kawrakow	Some more Q4_K and Q5_K speedup on CUDA (#2346)	commit \| commitdiff \| tree
2023-07-23	IgnacioFDM	Add gqa parameter support to the server (#2351)	commit \| commitdiff \| tree
2023-07-23	Johannes Gäßler	Fix __dp4a documentation (#2348)	commit \| commitdiff \| tree
2023-07-23	wzy	common : n_threads == -1 uses std::thread::hardware_con...	commit \| commitdiff \| tree
2023-07-23	slaren	fix n_tasks (#2342)	commit \| commitdiff \| tree
2023-07-23	slaren	ggml: move op parameters from tensors to ggml_tensor...	commit \| commitdiff \| tree
2023-07-23	Georgi Gerganov	llama : grouped-query attention + LLaMAv2 70B support...	commit \| commitdiff \| tree
2023-07-23	maddes8cht	llama : print help to stdout (#2338)	commit \| commitdiff \| tree
2023-07-23	wzy	flake : support `nix build '.#opencl'` (#2337)	commit \| commitdiff \| tree
2023-07-23	Christian Demsar	llama : print max tensor size to stderr (#2336)	commit \| commitdiff \| tree
2023-07-23	Jose Maldonado	make : fix CLBLAST compile support in FreeBSD (#2331)	commit \| commitdiff \| tree
2023-07-23	AustinMroz	examples : simplify vim plugin (#2327)	commit \| commitdiff \| tree
2023-07-23	Jiahao Li	metal : support bcast add & dup & cont op (#2323)	commit \| commitdiff \| tree
2023-07-23	Kawrakow	Speed up Q4_K (#2322)	commit \| commitdiff \| tree
2023-07-22	Johannes Gäßler	CUDA: Fixed 7b q3_K_S with mul_mat_vec_q (#2313)	commit \| commitdiff \| tree
2023-07-22	Georgi Gerganov	llama : optimize memory buffers (#2325)	commit \| commitdiff \| tree
2023-07-22	klosax	Perplexity: Compute scores correlated to HellaSwag...	commit \| commitdiff \| tree
2023-07-22	whoreson	examples : basic VIM plugin	commit \| commitdiff \| tree
2023-07-22	Georgi Gerganov	ci : fix args	commit \| commitdiff \| tree
2023-07-22	Georgi Gerganov	ci : add 7B CUDA tests (#2319)	commit \| commitdiff \| tree
2023-07-21	Richard Roberson	examples : add easy python script to create quantized...	commit \| commitdiff \| tree
2023-07-21	Kawrakow	Custom RoPE + bettter memory management for CUDA (...	commit \| commitdiff \| tree
2023-07-21	Kawrakow	Faster Q3_K implementation on Metal (#2307)	commit \| commitdiff \| tree
2023-07-21	Georgi Gerganov	ggml : fix the rope fix (513f8619535a64fa9ace808cdcbcf6...	commit \| commitdiff \| tree
2023-07-21	Ikko Eltociear...	examples : fix typo in minigpt4.py (#2298)	commit \| commitdiff \| tree
2023-07-21	Georgi Gerganov	ggml : fix rope args order + assert (#2054)	commit \| commitdiff \| tree
2023-07-21	Georgi Gerganov	gitignore : fix final newline	commit \| commitdiff \| tree
2023-07-21	Guillaume ...	llama : remove cfg smooth factor as it is only a repara...	commit \| commitdiff \| tree
2023-07-21	Jose Maldonado	gitignore : changes for Poetry users + chat examples...	commit \| commitdiff \| tree
2023-07-21	Georgi Gerganov	make : fix indentation	commit \| commitdiff \| tree
2023-07-21	Georgi Gerganov	ci : fix MNT realpath usage (#2250)	commit \| commitdiff \| tree
2023-07-21	Sky Yan	make : support customized LLAMA_CUDA_NVCC and LLAMA_CUD...	commit \| commitdiff \| tree
2023-07-21	wzy	flake : remove intel mkl from flake.nix due to missing...	commit \| commitdiff \| tree
2023-07-21	Georgi Gerganov	llama : make tensor_split ptr instead of array (#2272)	commit \| commitdiff \| tree
2023-07-21	Jiří Podivín	make : add new target for test binaries (#2244)	commit \| commitdiff \| tree
2023-07-21	Hatsune Miku	MIKU MAYHEM: Upgrading the Default Model for Maximum...	commit \| commitdiff \| tree
2023-07-21	Kawrakow	Faster Q2_K on Metal (#2297)	commit \| commitdiff \| tree
2023-07-21	Przemysław...	make : fix embdinput library and server examples buildi...	commit \| commitdiff \| tree
2023-07-20	Kawrakow	Faster Q5_K and Q6_K on Metal (#2294)	commit \| commitdiff \| tree
2023-07-20	Kawrakow	Faster Q4_K on Metal (#2290)	commit \| commitdiff \| tree
2023-07-20	Georgi Gerganov	llama : fix regression from #2000 - could not load...	commit \| commitdiff \| tree
2023-07-20	Shouzheng Liu	metal: minor q4 optimization and reduce code size ...	commit \| commitdiff \| tree
2023-07-19	Rinne	llama : extend API to get max devices at runtime (...	commit \| commitdiff \| tree
2023-07-19	wzy	flake : update flake.nix (#2270)	commit \| commitdiff \| tree
2023-07-19	wzy	cmake : install targets (#2256)	commit \| commitdiff \| tree
2023-07-18	Georgi Gerganov	ci : integrate with ggml-org/ci (#2250)	commit \| commitdiff \| tree
2023-07-18	Georgi Gerganov	llama : shorten quantization descriptions	commit \| commitdiff \| tree
2023-07-17	Jiahao Li	Support dup & cont ops on CUDA (#2242)	commit \| commitdiff \| tree
2023-07-16	Alex Klinkhamer	llama : fix t_start_sample_us initialization warning...	commit \| commitdiff \| tree
2023-07-16	Qingyou Meng	ggml : fixed runtime bugs and compile errors related...	commit \| commitdiff \| tree
2023-07-16	Jiří Podivín	py : turn verify-checksum-models.py into executable...	commit \| commitdiff \| tree
2023-07-15	Xiao-Yong Jin	llama : add custom RoPE (#2054)	commit \| commitdiff \| tree
2023-07-14	Dave Della...	flake : add runHook preInstall/postInstall to installPh...	commit \| commitdiff \| tree
2023-07-14	wzy	make : use pkg-config for OpenBLAS (#2222)	commit \| commitdiff \| tree
2023-07-14	Bach Le	cuda : allocate all temporary ggml_tensor_extra_gpu...	commit \| commitdiff \| tree
2023-07-14	Evan Miller	ggml : fix static_assert with older compilers #2024...	commit \| commitdiff \| tree
2023-07-14	Bach Le	llama : add functions that work directly on model ...	commit \| commitdiff \| tree
2023-07-14	Ali Chraghi	build.zig : install config header (#2216)	commit \| commitdiff \| tree
2023-07-14	Shangning Xu	examples : fixed path typos in embd-input (#2214)	commit \| commitdiff \| tree
2023-07-14	Jiahao Li	cuda : support broadcast add & mul (#2192)	commit \| commitdiff \| tree
2023-07-14	Johannes Gäßler	CUDA: mul_mat_vec_q kernels for k-quants (#2203)	commit \| commitdiff \| tree
2023-07-14	James Reynolds	make : fix combination of LLAMA_METAL and LLAMA_MPI...	commit \| commitdiff \| tree
2023-07-14	Georgi Gerganov	ggml : sync (ggml_conv_2d, fix mul_mat bug, CUDA GLM...	commit \| commitdiff \| tree
2023-07-14	Kawrakow	Metal: faster Q4_0 and Q4_1 matrix x vector kernels...	commit \| commitdiff \| tree
2023-07-13	Howard Su	Revert "Support using mmap when applying LoRA (#2095...	commit \| commitdiff \| tree
2023-07-13	Howard Su	Fix compile error on Windows CUDA (#2207)	commit \| commitdiff \| tree
2023-07-13	Bodo Graumann	devops : add missing quotes to bash script (#2193)	commit \| commitdiff \| tree
2023-07-12	Shouzheng Liu	metal : new q4_0 matrix-vector kernel (#2188)	commit \| commitdiff \| tree
2023-07-12	Georgi Gerganov	ggml : broadcast mul_mat + conv batch support (#2199)	commit \| commitdiff \| tree
2023-07-12	Georgi Gerganov	ggml : add ggml_pool_1d and ggml_pool_2d	commit \| commitdiff \| tree
2023-07-12	Georgi Gerganov	cuda : add gelu support	commit \| commitdiff \| tree
2023-07-12	Howard Su	FP16 is supported in CM=6.0 (#2177)	commit \| commitdiff \| tree
2023-07-12	Johannes Gäßler	Fixed __dp4a compute capability: 6.0 -> 6.1 (#2189)	commit \| commitdiff \| tree
2023-07-12	Georgi Gerganov	ggml : revert CUDA broadcast changes from #2183 (#2191)	commit \| commitdiff \| tree
2023-07-11	Georgi Gerganov	ggml : sync (abort callback, mul / add broadcast, fix...	commit \| commitdiff \| tree
2023-07-11	Spencer Sutton	ggml : remove src0 and src1 from ggml_tensor and rename...	commit \| commitdiff \| tree
2023-07-11	Bach Le	llama : add classifier-free guidance (#2135)	commit \| commitdiff \| tree
2023-07-11	Jinwoo Jeong	docker : add '--server' option (#2174)	commit \| commitdiff \| tree
2023-07-11	Chad Brewbaker	readme : fix zig build instructions (#2171)	commit \| commitdiff \| tree
2023-07-11	Howard Su	Support using mmap when applying LoRA (#2095)	commit \| commitdiff \| tree
2023-07-11	LostRuins	Possible solution to allow K-quants on models with...	commit \| commitdiff \| tree
2023-07-10	Evan Miller	mpi : add support for distributed inference via MPI...	commit \| commitdiff \| tree
2023-07-09	oobabooga	llama : remove "first token must be BOS" restriction...	commit \| commitdiff \| tree
2023-07-09	Nigel Bosch	main : escape prompt prefix/suffix (#2151)	commit \| commitdiff \| tree
2023-07-09	JackJollimore	readme : update Termux instructions (#2147)	commit \| commitdiff \| tree
2023-07-09	clyang	ggml : fix buidling with Intel MKL but ask for "cblas...	commit \| commitdiff \| tree
2023-07-09	rankaiyx	readme : add more docs indexes (#2127)	commit \| commitdiff \| tree
2023-07-08	Johannes Gäßler	Fixed OpenLLaMA 3b CUDA mul_mat_vec_q (#2144)	commit \| commitdiff \| tree
2023-07-07	Johannes Gäßler	CUDA: add __restrict__ to mul mat vec kernels (#2140)	commit \| commitdiff \| tree
2023-07-07	dylan	docker : add support for CUDA in docker (#1461)	commit \| commitdiff \| tree
2023-07-07	Georgi Gerganov	ci : switch threads to 1 (#2138)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom