 Pavol Rusnak
|
489537e6cf
examples: add missing <ctime> include for time() (#1011)
|
2 years ago |
 nanahi
|
2d3481c721
Fix msys2 build error and warnings (#1009)
|
2 years ago |
 comex
|
74f5899df4
convert.py: Fix loading safetensors and ggml format on Windows (#991)
|
2 years ago |
 Stephan Walter
|
2f7c8e014e
Fix potential int8 overflow in non-SIMD vec_dot (#986)
|
2 years ago |
|
Stephan Walter
|
0ad964631f
Refactor ggml.c for future tensor types (#1001)
|
2 years ago |
 Georgi Gerganov
|
e95b6554b4
ggml : add Q8_0 quantization for intermediate results (#951)
|
2 years ago |
|
Georgi Gerganov
|
aa485cee33
ggml : use posix_memalign on non-Windows env
|
2 years ago |
 Ivan Komarov
|
c12b14b77f
benchmark : fix result validation in benchmark-q4_0-matmult (#987)
|
2 years ago |
 katsu560
|
106faaf297
cmake : add finding the OpenBLAS header file (#992)
|
2 years ago |
|
Pavol Rusnak
|
c85e03d12e
Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)
|
2 years ago |
|
Pavol Rusnak
|
489093548c
py : bump sentencepiece to 0.1.98 to support Python 3.11 (#976)
|
2 years ago |
|
Stephan Walter
|
93265e988a
make : fix dependencies, use auto variables (#983)
|
2 years ago |
|
Pavol Rusnak
|
c56b715269
Expose type name from ggml (#970)
|
2 years ago |
 Tomáš Pazdiora
|
f4d277ae17
main : alternative instruct mode (Vicuna support, etc.) (#863)
|
2 years ago |
 Kerfuffle
|
c9a59b70a5
ggml : add unary and binary map operations (#874)
|
2 years ago |
|
Pavol Rusnak
|
a32f7acc9f
py : cleanup dependencies (#962)
|
2 years ago |
|
Pavol Rusnak
|
43ffdefb74
py : fix flake8 and isort nitpicks (#960)
|
2 years ago |
|
Georgi Gerganov
|
1623a6e9b4
ggml : minor
|
2 years ago |
|
Georgi Gerganov
|
c14e0d2f23
ggml : always allocate buffers with size multiple of GGML_MEM_ALIGN
|
2 years ago |
|
comex
|
723dac55fa
py : new conversion script (#545)
|
2 years ago |
|
Georgi Gerganov
|
0f07cacb05
ggml : fix q4_1 dot product types
|
2 years ago |
 Howard Su
|
c5d70f5c9e
ggml : optimize rope function to avoid call powf in the tight loop (#807)
|
2 years ago |
 Gary Linscott
|
be87b6ed20
perplexity : add support for batch size to `--perplexity` (#407)
|
2 years ago |
 CRD716
|
0e07e6a839
common : remove unnecessary includes (#947)
|
2 years ago |
|
Georgi Gerganov
|
a3a2a0eda8
ggml : add GGML_DEFAULT_N_THREADS
|
2 years ago |
|
Georgi Gerganov
|
d990e3fffc
ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900)
|
2 years ago |
|
Georgi Gerganov
|
9190e8eac8
llama : merge llama_internal.h into llama.h
|
2 years ago |
|
Georgi Gerganov
|
c85980acd0
gitignore : benchmark
|
2 years ago |
|
Stephan Walter
|
6232f2d7fd
ggml : optimize non-SIMD Q4_0 vector dot product (#703)
|
2 years ago |
|
Pavol Rusnak
|
6c248707f5
ggml : introduce GGML_ALIGNED_MALLOC/GGML_ALIGNED_FREE macros (#884)
|
2 years ago |
