llama.cpp.git - llama.cpp

Age	Commit message (Expand)	Author
2023-07-22	CUDA: Fixed 7b q3_K_S with mul_mat_vec_q (#2313)	Johannes Gäßler
2023-07-22	llama : optimize memory buffers (#2325)	Georgi Gerganov
2023-07-22	Perplexity: Compute scores correlated to HellaSwag (#2312)	klosax
2023-07-22	examples : basic VIM plugin	whoreson
2023-07-22	ci : fix args	Georgi Gerganov
2023-07-22	ci : add 7B CUDA tests (#2319)	Georgi Gerganov
2023-07-21	examples : add easy python script to create quantized (k-bit support) GGML mo...	Richard Roberson
2023-07-21	Custom RoPE + bettter memory management for CUDA (#2295)	Kawrakow
2023-07-21	Faster Q3_K implementation on Metal (#2307)	Kawrakow
2023-07-21	ggml : fix the rope fix (513f8619535a64fa9ace808cdcbcf66211535f5c)	Georgi Gerganov
2023-07-21	examples : fix typo in minigpt4.py (#2298)	Ikko Eltociear Ashimine
2023-07-21	ggml : fix rope args order + assert (#2054)	Georgi Gerganov
2023-07-21	gitignore : fix final newline	Georgi Gerganov
2023-07-21	llama : remove cfg smooth factor as it is only a reparameterization of the gu...	Guillaume "Vermeille" Sanchez
2023-07-21	gitignore : changes for Poetry users + chat examples (#2284)	Jose Maldonado
2023-07-21	make : fix indentation	Georgi Gerganov
2023-07-21	ci : fix MNT realpath usage (#2250)	Georgi Gerganov
2023-07-21	make : support customized LLAMA_CUDA_NVCC and LLAMA_CUDA_CCBIN (#2275)	Sky Yan
2023-07-21	flake : remove intel mkl from flake.nix due to missing files (#2277)	wzy
2023-07-21	llama : make tensor_split ptr instead of array (#2272)	Georgi Gerganov
2023-07-21	make : add new target for test binaries (#2244)	Jiří Podivín
2023-07-21	MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)	Hatsune Miku
2023-07-21	Faster Q2_K on Metal (#2297)	Kawrakow
2023-07-21	make : fix embdinput library and server examples building on MSYS2 (#2235)	Przemysław Pawełczyk
2023-07-20	Faster Q5_K and Q6_K on Metal (#2294)	Kawrakow
2023-07-20	Faster Q4_K on Metal (#2290)	Kawrakow
2023-07-20	llama : fix regression from #2000 - could not load no-mmap models	Georgi Gerganov
2023-07-20	metal: minor q4 optimization and reduce code size (#2248)	Shouzheng Liu
2023-07-19	llama : extend API to get max devices at runtime (#2253)	Rinne
2023-07-19	flake : update flake.nix (#2270)	wzy
2023-07-19	cmake : install targets (#2256)	wzy
2023-07-18	ci : integrate with ggml-org/ci (#2250)	Georgi Gerganov
2023-07-18	llama : shorten quantization descriptions	Georgi Gerganov
2023-07-17	Support dup & cont ops on CUDA (#2242)	Jiahao Li
2023-07-17	llama : fix t_start_sample_us initialization warning (#2238)	Alex Klinkhamer
2023-07-16	ggml : fixed runtime bugs and compile errors related to GGML_PERF and GGML_DE...	Qingyou Meng
2023-07-16	py : turn verify-checksum-models.py into executable (#2245)	Jiří Podivín
2023-07-15	llama : add custom RoPE (#2054)	Xiao-Yong Jin
2023-07-14	flake : add runHook preInstall/postInstall to installPhase so hooks function ...	Dave Della Costa
2023-07-14	make : use pkg-config for OpenBLAS (#2222)	wzy
2023-07-14	cuda : allocate all temporary ggml_tensor_extra_gpu from a fixed-size buffer ...	Bach Le
2023-07-14	ggml : fix static_assert with older compilers #2024 (#2218)	Evan Miller
2023-07-14	llama : add functions that work directly on model (#2197)	Bach Le
2023-07-14	build.zig : install config header (#2216)	Ali Chraghi
2023-07-14	examples : fixed path typos in embd-input (#2214)	Shangning Xu
2023-07-14	cuda : support broadcast add & mul (#2192)	Jiahao Li
2023-07-14	CUDA: mul_mat_vec_q kernels for k-quants (#2203)	Johannes Gäßler
2023-07-14	make : fix combination of LLAMA_METAL and LLAMA_MPI (#2208)	James Reynolds
2023-07-14	ggml : sync (ggml_conv_2d, fix mul_mat bug, CUDA GLM rope)	Georgi Gerganov
2023-07-14	Metal: faster Q4_0 and Q4_1 matrix x vector kernels (#2212)	Kawrakow