You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
7a32fcb3b2
* ggml : add Q8_0 quantization format (rename the old one to Q8_1) * tests : fix test-quantize-fns * ggml : finalize Q8_0 implementation * ggml : use q4_0_q8_0 and q4_2_q8_0 * ggml : fix Q8_0 dot product bug (ARM) * ggml : Q8_0 unroll x2 * ggml : fix bug - using wrong block type * ggml : extend quantize_fns_t with "vec_dot_type" * ggml : fix Q8_0 to use 255 values out of 256 * ggml : fix assert using wrong QK4_2 instead of QK4_3 |
1 year ago | |
---|---|---|
.. | ||
benchmark | 1 year ago | |
embedding | 1 year ago | |
main | 1 year ago | |
perplexity | 1 year ago | |
quantize | 1 year ago | |
quantize-stats | 1 year ago | |
save-load-state | 1 year ago | |
CMakeLists.txt | 1 year ago | |
Miku.sh | 1 year ago | |
alpaca.sh | 1 year ago | |
chat-13B.bat | 2 years ago | |
chat-13B.sh | 2 years ago | |
chat.sh | 2 years ago | |
common.cpp | 1 year ago | |
common.h | 1 year ago | |
gpt4all.sh | 1 year ago | |
reason-act.sh | 2 years ago |