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-9cbf50c

9cbf50c0 · build : fix and ignore MSVC warnings (#1889) · Jun 16, 2023
master-3d01122

3d011226 · CUDA : faster k-quant dot kernels (#1862) · Jun 16, 2023
master-a09f919

a09f9195 · Fixed CUDA runtime version check (#1879) · Jun 15, 2023
master-bed9275

bed92756 · cmake : remove whitespaces · Jun 15, 2023
master-c36e81d

c36e81da · examples : add chat-vicuna.sh (#1854) · Jun 15, 2023
master-3559433

3559433f · cmake : set include path for OpenBlas (#1830) · Jun 15, 2023
master-69b34a0

69b34a0e · swift : Package compile breaks due to ggml-metal.metal (#1831) · Jun 15, 2023
master-cf267d1

cf267d1c · make : add train-text-from-scratch (#1850) · Jun 15, 2023
master-37e257c

37e257c4 · make : clean *.so files (#1857) · Jun 15, 2023
master-64cc19b

64cc19b4 · Fix the validation of main device (#1872) · Jun 15, 2023
master-4bfcc85

4bfcc855 · metal : parallel command buffer encoding (#1860) · Jun 15, 2023
master-6b8312e

6b8312e7 · Better error when using both LoRA + GPU layers (#1861) · Jun 15, 2023
master-254a7a7

254a7a7a · CUDA full GPU acceleration, KV cache in VRAM (#1827) · Jun 14, 2023
ci_cublas_linux-d9f3846

d9f38465 · ci: add linux binaries to release build · Jun 13, 2023
master-9254920

92549202 · baby-llama : fix operator!= (#1821) · Jun 13, 2023
master-e32089b

e32089b2 · train : improved training-from-scratch example (#1652) · Jun 13, 2023
master-2347e45

2347e45e · llama : do a warm-up eval at start for better timings (#1824) · Jun 13, 2023
master-74d4cfa

74d4cfa3 · Allow "quantizing" to f16 and f32 (#1787) · Jun 13, 2023
master-74a6d92

74a6d922 · Metal implementation for all k_quants (#1807) · Jun 12, 2023
master-e4caa8d

e4caa8da · ci : run when changing only the CUDA sources (#1800) · Jun 12, 2023