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

b3266

1c5eba6f · llama: Add attention and final logit soft-capping, update scaling factor to Gemma2 (#8197) · Jun 29, 2024
b3265

72272b83 · fix code typo in llama-cli (#8198) · Jun 29, 2024
b3264

8748d8ac · json: attempt to skip slow tests when running under emulator (#8189) · Jun 28, 2024
b3263

26a39bbd · Add MiniCPM, Deepseek V2 chat template + clean up `llama_chat_apply_template_internal` (#8172) · Jun 28, 2024
b3262

38373cfb · Add SPM infill support (#8016) · Jun 28, 2024
b3261

b851b3fb · cmake : allow user to override default options (#8178) · Jun 28, 2024
b3260

139cc621 · `json`: restore default additionalProperties to false, fix some pattern escapes (#8180) · Jun 28, 2024
b3259

e57dc620 · llama: Add support for Gemma2ForCausalLM (#8156) · Jun 27, 2024
b3258

a27aa50a · Add missing items in makefile (#8177) · Jun 28, 2024
b3256

558f44bf · CI: fix release build (Ubuntu+Mac) (#8170) · Jun 27, 2024
b3254

16791b8f · Add chatml fallback for cpp `llama_chat_apply_template` (#8160) · Jun 27, 2024
b3252

97877eb1 · Control vector loading fixes (#8137) · Jun 27, 2024
b3250

6030c612 · Add Qwen2MoE 57B-A14B model identifier (#8158) · Jun 27, 2024
b3249

85a267da · CUDA: fix MMQ stream-k for --split-mode row (#8167) · Jun 27, 2024
b3248

f675b20a · Added support for Viking pre-tokenizer (#8135) · Jun 27, 2024
b3246

ac146628 · Fix llama-android.cpp for error - "common/common.h not found" (#8145) · Jun 27, 2024
b3245

9b31a40c · clip : suppress unused variable warnings (#8105) · Jun 27, 2024
b3243

ae5d0f4b · ci : publish new docker images only when the files change (#8142) · Jun 26, 2024
b3242

31ec3993 · ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140) · Jun 26, 2024
b3241

c7ab7b61 · make : fix missing -O3 (#8143) · Jun 26, 2024

1
…
69
70
71
72
73
74
75
76
77
…
178