 bandoti
|
531cb1c233
Skip searching root path for cross-compile builds (#10383)
|
1 year ago |
 Jeff Bolz
|
f139d2ea61
vulkan: remove use of null initializer (#10372)
|
1 year ago |
 Georgi Gerganov
|
2eb76b2a5e
flake.lock: Update (#10346)
|
1 year ago |
 0cc4m
|
9b75f03cd2
Vulkan: Fix device info output format specifiers (#10366)
|
1 year ago |
 Johannes Gäßler
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
1 year ago |
|
Johannes Gäßler
|
76e9e58b78
CUDA: fix MMV kernel being used for FP16 src1 (#10357)
|
1 year ago |
|
Johannes Gäßler
|
ce2e59ba10
CMake: fix typo in comment [no ci] (#10360)
|
1 year ago |
 Diego Devesa
|
be5caccef9
llama : only use default buffer types for the KV cache (#10358)
|
1 year ago |
|
Georgi Gerganov
|
20a780c7b6
gitignore : ignore local run scripts [no ci]
|
1 year ago |
|
Georgi Gerganov
|
cf32a9b93a
metal : refactor kernel args into structs (#10238)
|
1 year ago |
 FirstTimeEZ
|
a43178299c
ggml : fix undefined reference to 'getcpu' (#10354)
|
1 year ago |
|
Johannes Gäßler
|
c3ea58aca4
CUDA: remove DMMV, consolidate F16 mult mat vec (#10318)
|
1 year ago |
|
Johannes Gäßler
|
467576b6cc
CMake: default to -arch=native for CUDA build (#10320)
|
1 year ago |
|
Diego Devesa
|
eda7e1d4f5
ggml : fix possible buffer use after free in sched reserve (#9930)
|
1 year ago |
|
Georgi Gerganov
|
24203e9dd7
ggml : inttypes.h -> cinttypes (#0)
|
1 year ago |
|
Georgi Gerganov
|
5d9e59979c
ggml : adapt AMX to tensor->grad removal (#0)
|
1 year ago |
|
Georgi Gerganov
|
a4200cafad
make : add ggml-opt (#0)
|
1 year ago |
|
Georgi Gerganov
|
84274a10c3
tests : remove test-grad0
|
1 year ago |
|
Georgi Gerganov
|
68fcb4759c
ggml : fix compile warnings (#0)
|
1 year ago |
|
Johannes Gäßler
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
1 year ago |
|
Georgi Gerganov
|
5c9a8b22b1
scripts : update sync
|
1 year ago |
|
FirstTimeEZ
|
0fff7fd798
docs : vulkan build instructions to use git bash mingw64 (#10303)
|
1 year ago |
|
Johannes Gäßler
|
4e54be0ec6
llama/ex: remove --logdir argument (#10339)
|
1 year ago |
|
Georgi Gerganov
|
db4cfd5dbc
llamafile : fix include path (#0)
|
1 year ago |
|
Georgi Gerganov
|
8ee0d09ae6
make : auto-determine dependencies (#0)
|
1 year ago |
 MaggotHATE
|
bcdb7a2386
server: (web UI) Add samplers sequence customization (#10255)
|
1 year ago |
|
Georgi Gerganov
|
f245cc28d4
scripts : fix missing key in compare-llama-bench.py (#10332)
|
1 year ago |
|
Jeff Bolz
|
772703c8ff
vulkan: Optimize some mat-vec mul quant shaders (#10296)
|
1 year ago |
|
FirstTimeEZ
|
dd3a6ce9f8
vulkan : add cmake preset debug/release (#10306)
|
1 year ago |
 Dan Johansson
|
1e58ee1318
ggml : optimize Q4_0 into Q4_0_X_Y repack (#10324)
|
1 year ago |
