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-d7d2e6a

d7d2e6a0 · server: add option to output probabilities for completion (#1962) · Jul 03, 2023
master-46088f7

46088f72 · ggml : fix build with OpenBLAS (close #2066) · Jul 02, 2023
master-0bc2cdf

0bc2cdfc · Better CUDA synchronization logic (#2057) · Jul 01, 2023
master-2f8cd97

2f8cd979 · metal : release buffers when freeing metal context (#2062) · Jul 01, 2023
master-79f634a

79f634a1 · embd-input : fix returning ptr to temporary · Jul 01, 2023
master-b8c8dda

b8c8dda7 · Use unsigned for random seed (#2006) · Jun 29, 2023
master-d3494bb

d3494bb8 · llama : replacing auto &kv with const auto &kv (#2041) · Jun 28, 2023
master-5b351e9

5b351e94 · cuda : remove nchannels_x argument from mul_mat_vec_nc_f16_f32 (#2028) · Jun 28, 2023
master-6432aab

6432aabb · cuda : fix missing const qualifier in casts (#2027) · Jun 28, 2023
master-b922bc3

b922bc35 · llama : remove shards weight file support (#2000) · Jun 28, 2023
master-7f9753f

7f9753fa · CUDA GPU acceleration for LoRAs + f16 models (#1970) · Jun 28, 2023
master-9d23589

9d23589d · fix pthreads setaffinity usage on android (#2020) · Jun 27, 2023
master-0be54f7

0be54f75 · baby-llama : fix build after ggml_rope change (#2016) · Jun 27, 2023
master-eaa6ca5

eaa6ca5a · ggml : increase max tensor name + clean up compiler warnings in train-text (#1988) · Jun 26, 2023
master-c824d2e

c824d2e3 · ggml : avoid conv 2d kernel round up · Jun 26, 2023
master-b853d45

b853d456 · ggml : add NUMA support (#1556) · Jun 26, 2023
master-9225bae

9225baef · k-quants : fix indentation · Jun 26, 2023
master-a84ab1d

a84ab1da · tests : fix quantize perf (#1990) · Jun 26, 2023
master-5743ca8

5743ca80 · k-quants : add AVX support to dot functions (#1916) · Jun 26, 2023
master-6769e94

6769e944 · k-quants : support for super-block size of 64 (#2001) · Jun 26, 2023