为了安全，强烈建议开启2FA双因子认证：User Settings -> Account -> Enable two-factor authentication！！！

Tags

Tags give the ability to mark specific points in history as being important

master-42c7c2e

42c7c2e2 · make : support customized LLAMA_CUDA_NVCC and LLAMA_CUDA_CCBIN (#2275) · Jul 21, 2023
master-78a3d13

78a3d134 · flake : remove intel mkl from flake.nix due to missing files (#2277) · Jul 21, 2023
master-ae178ab

ae178ab4 · llama : make tensor_split ptr instead of array (#2272) · Jul 21, 2023
master-54e3bc7

54e3bc76 · make : add new target for test binaries (#2244) · Jul 21, 2023
master-9cf022a

9cf022a1 · make : fix embdinput library and server examples building on MSYS2 (#2235) · Jul 21, 2023
master-fff0e0e

fff0e0ea · llama : fix regression from #2000 - could not load no-mmap models · Jul 20, 2023
master-294f424

294f4245 · llama : extend API to get max devices at runtime (#2253) · Jul 19, 2023
master-45a1b07

45a1b07e · flake : update flake.nix (#2270) · Jul 19, 2023
master-b1f4290

b1f42909 · cmake : install targets (#2256) · Jul 19, 2023
master-d01bccd

d01bccde · ci : integrate with ggml-org/ci (#2250) · Jul 18, 2023
master-6cbf9df

6cbf9dfb · llama : shorten quantization descriptions · Jul 18, 2023
master-7568d1a

7568d1a2 · Support dup & cont ops on CUDA (#2242) · Jul 17, 2023
master-b764743

b7647436 · llama : fix t_start_sample_us initialization warning (#2238) · Jul 17, 2023
master-672dda1

672dda10 · ggml : fixed runtime bugs and compile errors related to GGML_PERF and GGML_DEBUG (#2219) · Jul 16, 2023
master-6e7cca4

6e7cca40 · llama : add custom RoPE (#2054) · Jul 15, 2023
master-7dabc66

7dabc66f · make : use pkg-config for OpenBLAS (#2222) · Jul 14, 2023
master-7cdd30b

7cdd30bf · cuda : allocate all temporary ggml_tensor_extra_gpu from a fixed-size buffer (#2220) · Jul 14, 2023
master-e8035f1

e8035f14 · ggml : fix static_assert with older compilers #2024 (#2218) · Jul 14, 2023
master-7513b7b

7513b7b0 · llama : add functions that work directly on model (#2197) · Jul 14, 2023
master-206e01d

206e01de · cuda : support broadcast add & mul (#2192) · Jul 14, 2023