 Georgi Gerganov
|
4caebf6d40
gitignore : vdot
|
2 anni fa |
|
Georgi Gerganov
|
dcdd65e296
ggml : optimize ggml_vec_dot_q4_0_q8_0() using vectorized accumulators
|
2 anni fa |
 Kawrakow
|
5ecff35151
Adding a simple program to measure speed of dot products (#1041)
|
2 anni fa |
|
Georgi Gerganov
|
7faa7460f0
readme : update hot topics about new LoRA functionality
|
2 anni fa |
|
Georgi Gerganov
|
5af8e32238
ci : do not run on drafts
|
2 anni fa |
 Ivan Komarov
|
42747220b4
Do not close file after mmap (Windows version) (#1034)
|
2 anni fa |
 Atsushi Tatsuma
|
e9298af389
readme : add Ruby bindings (#1029)
|
2 anni fa |
 Cameron
|
4ad73137a1
add 4_0 to default outfile namestr dict (#1031)
|
2 anni fa |
 slaren
|
315a95a4d3
Add LoRA support (#820)
|
2 anni fa |
 Arik Poznanski
|
efd05648c8
llama : well-defined static initialization of complex objects (#927)
|
2 anni fa |
|
Georgi Gerganov
|
eb17a026fd
quantize-stats : fix bug in --type argument
|
2 anni fa |
|
Georgi Gerganov
|
69b740289f
ggml : avoid using ggml_fp16_to_fp32() and ggml_fp32_to_fp16() in ggml.c
|
2 anni fa |
|
Ivan Komarov
|
f266259ad9
Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933)
|
2 anni fa |
|
slaren
|
47f61aaa5f
Fix: do not close file on mmap (#1017)
|
2 anni fa |
|
Georgi Gerganov
|
3173a62eb9
stdout : vertical align outputs for better readibility
|
2 anni fa |
 Pavol Rusnak
|
489537e6cf
examples: add missing <ctime> include for time() (#1011)
|
2 anni fa |
 nanahi
|
2d3481c721
Fix msys2 build error and warnings (#1009)
|
2 anni fa |
 comex
|
74f5899df4
convert.py: Fix loading safetensors and ggml format on Windows (#991)
|
2 anni fa |
 Stephan Walter
|
2f7c8e014e
Fix potential int8 overflow in non-SIMD vec_dot (#986)
|
2 anni fa |
|
Stephan Walter
|
0ad964631f
Refactor ggml.c for future tensor types (#1001)
|
2 anni fa |
|
Georgi Gerganov
|
e95b6554b4
ggml : add Q8_0 quantization for intermediate results (#951)
|
2 anni fa |
|
Georgi Gerganov
|
aa485cee33
ggml : use posix_memalign on non-Windows env
|
2 anni fa |
|
Ivan Komarov
|
c12b14b77f
benchmark : fix result validation in benchmark-q4_0-matmult (#987)
|
2 anni fa |
 katsu560
|
106faaf297
cmake : add finding the OpenBLAS header file (#992)
|
2 anni fa |
|
Pavol Rusnak
|
c85e03d12e
Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)
|
2 anni fa |
|
Pavol Rusnak
|
489093548c
py : bump sentencepiece to 0.1.98 to support Python 3.11 (#976)
|
2 anni fa |
|
Stephan Walter
|
93265e988a
make : fix dependencies, use auto variables (#983)
|
2 anni fa |
|
Pavol Rusnak
|
c56b715269
Expose type name from ggml (#970)
|
2 anni fa |
 Tomáš Pazdiora
|
f4d277ae17
main : alternative instruct mode (Vicuna support, etc.) (#863)
|
2 anni fa |
 Kerfuffle
|
c9a59b70a5
ggml : add unary and binary map operations (#874)
|
2 anni fa |
