slaren
|
f3c1e6aeaa
|
update tests and examples
|
2024-11-04 19:42:09 +02:00 |
|
Georgi Gerganov
|
336c10a4c3
|
examples : adapt to ggml.h changes (#0)
ggml-ci
|
2024-09-20 22:03:57 +03:00 |
|
Bryan Lozano
|
30626ea6e0
|
examples : fix simple (#770)
* Update README.md
Correcting matrix multiplication expected result.
* Update simple-ctx.cpp
Fix incorrect striding through output.
* simple : update readme
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
2024-03-22 09:17:34 +02:00 |
|
leejet
|
274680868e
|
add some new ops, fix some operators and add batch operations to certain operators. (#747)
* cuda: fix group_norm
* cuda: add batch inference support for ggml_pad/ggml_upscale
* add ggml_arrange
* add ggml_timestep_embedding
* update ggml_arange/ggml_timestep_embedding tests
* cuda: fix im2col
* add ggml_arange/ggml_timestep_embbeding support for metal backend
* fix some bugs
* fix some bugs
* Update include/ggml/ggml.h
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update src/ggml-cuda.cu
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update src/ggml-metal.m
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update src/ggml-metal.m
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update src/ggml-metal.metal
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* modify according to the review comments
* ggml : fix compile warnings + code style
* ggml : normalize compute_forward calls + fix seg fault in debug
* minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
|
2024-03-03 13:23:52 +01:00 |
|
Steward Garcia
|
d9cd6b5709
|
ggml : add simple example (#713)
* add simple example for explain memory management and basic operation of ggml
|
2024-02-28 11:40:12 -05:00 |
|