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-b24c304

b24c3049 · Added tokens per second to info prints (#1928) · Jun 18, 2023
master-0ede372

0ede372a · Fixed incorrectly applying RMS norm twice (#1925) · Jun 18, 2023
master-8596af4

8596af42 · ggml : fix bug in ggml_compute_forward_add_q_f32 (#1918) · Jun 18, 2023
master-8ab8ba6

8ab8ba62 · llama : prevent usage of k-quants when tensor size is not a multiple of 256 (#1921) · Jun 18, 2023
master-90cc59d

90cc59d6 · examples : fix examples/metal (#1920) · Jun 18, 2023
master-ce2c7d7

ce2c7d72 · metal : handle buffers larger than device's maxBufferLength (#1826) · Jun 18, 2023
master-57cd694

57cd6946 · cmake : add CUDA_ARCHITECTURES to new target ggml_static (#1917) · Jun 18, 2023
master-b241649

b2416493 · make : do not print help for simple example · Jun 17, 2023
master-4f9c43e

4f9c43e3 · minor : warning fixes · Jun 17, 2023
master-2c9380d

2c9380dd · Only one CUDA stream per device for async compute (#1898) · Jun 17, 2023
master-051e1b0

051e1b0e · llama : fix kv_cache `n` init (close #1903) · Jun 17, 2023
master-86c7571

86c75718 · make : update for latest Arch (#1701) · Jun 17, 2023
master-3d59ec5

3d59ec59 · ggml : fix warnings under MSVC (#1908) · Jun 17, 2023
master-794db3e

794db3e7 · Server Example Refactor and Improvements (#1570) · Jun 17, 2023
master-b4c6f46

b4c6f46f · Allow cmake to build ggml as a library (#1896) · Jun 17, 2023
master-d411968

d411968e · opencl : support k-quants (#1836) · Jun 16, 2023
master-b41b4ca

b41b4cad · examples : add "simple" (#1840) · Jun 16, 2023
master-13fe9d2

13fe9d2d · cmake : add auto detection of BLAS_INCLUDE_DIRS (#1886) · Jun 16, 2023
master-ac3b886

ac3b8869 · llama : fix embd when offloading non-repeating layers (#1891) · Jun 16, 2023
master-5b9ccaf

5b9ccaf1 · Fixed possible macro redefinition (#1892) · Jun 16, 2023