 Shouzheng Liu
|
dadbed99e6
metal : fix synchronization in new matrix multiplication kernel (#2686)
|
il y a 2 ans |
 Kawrakow
|
cb1c0727bd
HellaSwag: split token evaluation into batches if needed (#2681)
|
il y a 2 ans |
 slaren
|
9e232f0234
ggml : move all type info to ggml_type_traits (#2663)
|
il y a 2 ans |
|
Kawrakow
|
5e9ff54a67
More efficient Hellaswag implementation (#2677)
|
il y a 2 ans |
 Georgi Gerganov
|
1f0bccb279
server : better default prompt (#2646)
|
il y a 2 ans |
 Jhen-Jie Hong
|
f63564adfa
server : update xxd usage for older versions compatibility (#2649)
|
il y a 2 ans |
 Adrian
|
2d8b76a110
Add link to clojure bindings to Readme. (#2659)
|
il y a 2 ans |
|
Georgi Gerganov
|
7af633aec3
readme : incoming BREAKING CHANGE
|
il y a 2 ans |
|
slaren
|
097e121e2f
llama : add benchmark example (#2626)
|
il y a 2 ans |
 mdrokz
|
eaf98c2649
readme : add link to Rust bindings (#2656)
|
il y a 2 ans |
|
Georgi Gerganov
|
e9b12c332e
perplexity : more meaningful ETA number - 2 decimal points
|
il y a 2 ans |
 Evan Jones
|
604b8bdfa6
Fix unicode in grammars (fixes #2501) (#2553)
|
il y a 2 ans |
 staviq
|
10151bee2e
server : support for saving templates in browser LocalStorage (#2486)
|
il y a 2 ans |
 Johannes Gäßler
|
0992a7b8b1
README: fix LLAMA_CUDA_MMV_Y documentation (#2647)
|
il y a 2 ans |
 Henri Vasserman
|
6ddeefad9b
[Zig] Fixing Zig build and improvements (#2554)
|
il y a 2 ans |
 Kerfuffle
|
8dae7ce684
Add --cfg-negative-prompt-file option for examples (#2591)
|
il y a 2 ans |
|
Georgi Gerganov
|
a73ccf1aa3
llama : replace (permute + reshape + view_1d) with (view_3d) (#2538)
|
il y a 2 ans |
 drbh
|
7cf54e1f74
tests : adds simple llama grammar tests (#2618)
|
il y a 2 ans |
|
Shouzheng Liu
|
a872a2b28e
ggml-alloc : fix discrepency between measure&eval (#2639)
|
il y a 2 ans |
 Kolen Cheung
|
0919a0f73d
cmake : install ggml-meta.metal if LLAMA_METAL (#2449)
|
il y a 2 ans |
|
Jhen-Jie Hong
|
ed53db86c3
metal : print error of load pipeline state (#2564)
|
il y a 2 ans |
|
Shouzheng Liu
|
fc8ef549e5
metal : enable ggml-alloc (#2627)
|
il y a 2 ans |
|
Shouzheng Liu
|
bf83bff674
metal : matrix-matrix multiplication kernel (#2615)
|
il y a 2 ans |
|
Georgi Gerganov
|
b5ffb2849d
scripts : add helper script to get wikitext
|
il y a 2 ans |
|
Jhen-Jie Hong
|
3ebb00935f
server : add missing /json-schema-to-grammar.mjs (#2616)
|
il y a 2 ans |
|
Jhen-Jie Hong
|
d783f7982e
metal : return null instead of exit(1) (#2573)
|
il y a 2 ans |
 Cheng Shao
|
d75561df20
server : add --numa support (#2524)
|
il y a 2 ans |
 Kamil Tomšík
|
348acf188c
llama : add missing enum keyword in function signatures (#2610)
|
il y a 2 ans |
|
Johannes Gäßler
|
1cd06fa25e
CUDA: launch_bounds, small q4_K, q5_K mmq refactor (#2596)
|
il y a 2 ans |
|
Jhen-Jie Hong
|
2feb8934eb
server : fix default grammar by use empty string in the UI (#2604)
|
il y a 2 ans |
