 Georgi Gerganov
|
f83351f9a6
imatrix : migrate to gpt_params (#7771)
|
1 anno fa |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
1 anno fa |
|
Georgi Gerganov
|
554c247caf
ggml : remove OpenCL (#7735)
|
1 anno fa |
 0cc4m
|
3d7ebf6312
Vulkan Mixture of Experts (MoE) support (#7628)
|
1 anno fa |
 Brian
|
d298382ad9
main: replace --no-special with --special (#7534)
|
1 anno fa |
 Justine Tunney
|
00c6390793
main : don't print special tokens with --grammar (#6923)
|
1 anno fa |
 Masaya, Kato
|
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
|
1 anno fa |
 Xuan Son Nguyen
|
902184dd3a
fix missing slash in `fs_get_cache_directory()` (#7503)
|
1 anno fa |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
1 anno fa |
 Amir
|
11474e756d
examples: cache hf model when --model not provided (#7353)
|
1 anno fa |
 Herman Semenov
|
359cbe3f46
ggml-quants, llama : removed excess checks (#7274)
|
1 anno fa |
 Radoslav Gerganov
|
5e31828d3e
ggml : add RPC backend (#6829)
|
1 anno fa |
|
Justine Tunney
|
4e3880978f
Fix memory bug in grammar parser (#7194)
|
1 anno fa |
 HanishKVC
|
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
|
1 anno fa |
 Johannes Gäßler
|
c12452c7ae
JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143)
|
1 anno fa |
 Dawid Potocki
|
83330d8cd6
main : add --conversation / -cnv flag (#7108)
|
1 anno fa |
 viric
|
fcd84a0f5a
Fix Linux /sys cpu path to guess number of cores (#7064)
|
1 anno fa |
|
Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
1 anno fa |
 Olivier Chafik
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
1 anno fa |
 cpumaxx
|
ffe666572f
llava-cli : multiple images (#6969)
|
1 anno fa |
|
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
1 anno fa |
 Pierrick Hymbert
|
0c4d489e29
quantize: add imatrix and dataset metadata in GGUF (#6658)
|
1 anno fa |
 slaren
|
017e6999b5
add basic tensor data validation function (#6884)
|
1 anno fa |
 Kyle Mistele
|
37246b1031
common : revert showing control tokens by default for server (#6860)
|
1 anno fa |
|
Johannes Gäßler
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
1 anno fa |
|
Georgi Gerganov
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
1 anno fa |
|
Georgi Gerganov
|
aed82f6837
common : try to fix Android CI (#6780)
|
1 anno fa |
|
Justine Tunney
|
8cc91dc63c
ggml : add llamafile sgemm (#6414)
|
1 anno fa |
|
Olivier Chafik
|
7593639ce3
`main`: add --json-schema / -j flag (#6659)
|
1 anno fa |
|
Pierrick Hymbert
|
b804b1ef77
eval-callback: Example how to use eval callback for debugging (#6576)
|
1 anno fa |
