katsu560
|
60f8c361ca
ggml : add AVX support based on AVX2 code (#1430)
|
2 лет назад |
Georgi Gerganov
|
601a033475
ggml : add GGML_QNT_VERSION to track quantization format changes
|
2 лет назад |
Georgi Gerganov
|
08737ef720
cuda : fix convert function (#1412)
|
2 лет назад |
Georgi Gerganov
|
bda4d7c215
make : fix PERF build with cuBLAS
|
2 лет назад |
Georgi Gerganov
|
5a5aeb1e91
llama : fix unused warning
|
2 лет назад |
Georgi Gerganov
|
66841fdb0e
ggml : multi-thread mul and diag_mask ops (#1428)
|
2 лет назад |
Johannes Gäßler
|
905d87b70a
ggml : GPU-accelerated token generation (#1412)
|
2 лет назад |
xaedes
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
2 лет назад |
Georgi Gerganov
|
f048af0230
ggml : sync alibi fix from ggml repo
|
2 лет назад |
3ooabkhxtn
|
ac0cd259d5
Adding SSE instructions to ggml_vec_dot_q4_0_q8_0 (#1413)
|
2 лет назад |
Georgi Gerganov
|
0cd22e190a
llama : fix various warnings
|
2 лет назад |
Rinne
|
6456a4eb9f
embedding : remove unused code (#1426)
|
2 лет назад |
Georgi Gerganov
|
cdd5350892
readme : update Q4_0 perplexities
|
2 лет назад |
Georgi Gerganov
|
738ace394a
llama : free ggml context in set / copy state data (close #1425)
|
2 лет назад |
Henri Vasserman
|
699b1ad7fe
opencl : fix kernels for the new formats (#1422)
|
2 лет назад |
Georgi Gerganov
|
fb62f92433
llama : fix --mtest option (close #1414)
|
2 лет назад |
Johannes Gäßler
|
773ee249fb
CLI args use - instead of _, backwards compatible (#1416)
|
2 лет назад |
slaren
|
553fd4d4b5
Add clang-tidy reviews to CI (#1407)
|
2 лет назад |
Rinne
|
089b1c93ba
readme : add C#/.NET bindings repo (#1409)
|
2 лет назад |
Georgi Gerganov
|
b9fd7eee57
ggml : remove bit shuffling (#1405)
|
2 лет назад |
CRD716
|
b608b55a3e
prompts : model agnostic DAN (#1304)
|
2 лет назад |
Evan Jones
|
cf348a60e0
main : add option to save full output to session (#1338)
|
2 лет назад |
DannyDaemonic
|
e6a46b0ed1
Locale fix for Windows (#1379)
|
2 лет назад |
Sami Farin
|
9f8dbc4787
use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler (#1314)
|
2 лет назад |
DannyDaemonic
|
41654efea8
Interface improvements and `--multiline-input` (previously `--author-mode`) (#1040)
|
2 лет назад |
Georgi Gerganov
|
56551bc11f
readme : add notice about upcoming breaking change
|
2 лет назад |
AlpinDale
|
fe60904eef
readme : add TOC and Pygmalion instructions (#1359)
|
2 лет назад |
Pavol Rusnak
|
003ba2fb43
llama : fix hparams shadow (#1367)
|
2 лет назад |
Georgi Gerganov
|
f9a6364912
llama : require first token to be BOS (#1303)
|
2 лет назад |
ubik2
|
95078cc554
convert: add ability to convert safetensors files (#1276)
|
2 лет назад |