 Johannes Gäßler
|
16b9cd1939
Convert vector to f16 for dequantize mul mat vec (#1913)
|
2 jaren geleden |
 Mike
|
e1886cf4fe
readme : update Android build instructions (#1922)
|
2 jaren geleden |
|
Johannes Gäßler
|
2c9380dd2f
Only one CUDA stream per device for async compute (#1898)
|
2 jaren geleden |
 Gustavo Rocha Dias
|
bac19927c3
readme : alternative way to build for Android with CLBlast. (#1828)
|
2 jaren geleden |
 Aisuko
|
059e99066d
doc : fix wrong address of BLIS.md (#1772)
|
2 jaren geleden |
 Georgi Gerganov
|
4dc62c545d
readme : add June roadmap
|
2 jaren geleden |
 Yuval Peled
|
f4c55d3bd7
docs : add performance troubleshoot + example benchmark documentation (#1674)
|
2 jaren geleden |
 Foul-Tarnished
|
f1465624c2
readme : fix typo (#1700)
|
2 jaren geleden |
|
Georgi Gerganov
|
827f5eda91
readme : update hot topics
|
2 jaren geleden |
|
Georgi Gerganov
|
ecb217db4f
llama : Metal inference (#1642)
|
2 jaren geleden |
 Henri Vasserman
|
d8bd0013e8
Add info about CUDA_VISIBLE_DEVICES (#1682)
|
2 jaren geleden |
|
Henri Vasserman
|
97c9b77c4f
Add documentation about CLBlast (#1604)
|
2 jaren geleden |
 Evan Jones
|
c31bbe934b
readme : add docs for chat-persistent.sh (#1568)
|
2 jaren geleden |
 Zenix
|
b8ee340abe
feature : support blis and other blas implementation (#1536)
|
2 jaren geleden |
|
Georgi Gerganov
|
ea600071cb
Revert "feature : add blis and other BLAS implementation support (#1502)"
|
2 jaren geleden |
|
Zenix
|
07e9ace0f9
feature : add blis and other BLAS implementation support (#1502)
|
2 jaren geleden |
|
Georgi Gerganov
|
2d5db48371
ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508)
|
2 jaren geleden |
 David Kennedy
|
79e3efb0e9
readme : adds WizardLM to the list of supported models (#1485)
|
2 jaren geleden |
|
Georgi Gerganov
|
cdd5350892
readme : update Q4_0 perplexities
|
2 jaren geleden |
 Rinne
|
089b1c93ba
readme : add C#/.NET bindings repo (#1409)
|
2 jaren geleden |
|
Georgi Gerganov
|
b9fd7eee57
ggml : remove bit shuffling (#1405)
|
2 jaren geleden |
|
Georgi Gerganov
|
56551bc11f
readme : add notice about upcoming breaking change
|
2 jaren geleden |
 AlpinDale
|
fe60904eef
readme : add TOC and Pygmalion instructions (#1359)
|
2 jaren geleden |
|
Georgi Gerganov
|
f9a6364912
llama : require first token to be BOS (#1303)
|
2 jaren geleden |
|
Johannes Gäßler
|
1f48b0abcf
Documented CUDA reproducibility, added warning (#1346)
|
2 jaren geleden |
 DaniAndTheWeb
|
173d0e6419
makefile: automatic Arch Linux detection (#1332)
|
2 jaren geleden |
 Pavol Rusnak
|
921dcee00a
readme: add missing info (#1324)
|
2 jaren geleden |
 44670
|
360cfe5bec
readme : add OpenBuddy link (#1321)
|
2 jaren geleden |
|
Georgi Gerganov
|
bca9ad938a
minor : fix whitespaces (#1302)
|
2 jaren geleden |
 KASR
|
b0c71c7b6d
scripts : platform independent script to verify sha256 checksums (#1203)
|
2 jaren geleden |
