Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

sync : ggml #9362

Merged
merged 11 commits into from
Sep 8, 2024
Merged

sync : ggml #9362

merged 11 commits into from
Sep 8, 2024

Conversation

ggerganov
Copy link
Member

No description provided.

@ggerganov ggerganov changed the title ggml : sync sync : ggml Sep 8, 2024
@github-actions github-actions bot added script Script related testing Everything test related Nvidia GPU Issues specific to Nvidia GPUs Vulkan Issues specific to the Vulkan backend ggml changes relating to the ggml tensor library for machine learning labels Sep 8, 2024
smeso and others added 10 commits September 8, 2024 09:35
…/934)

* ggml_cont: fix issue with transposed tensors when one dimension is 1

when using multiple threads, it is not enough
to check for the tensors to be contiguous for
ggml_compute_forward_dup_same_cont to work correctly.
The tensors strides also need to match.

Signed-off-by: Salvatore Mesoraca <[email protected]>

* Add ggml_cont tests

Signed-off-by: Salvatore Mesoraca <[email protected]>

* Remove dead code

it isn't possible to reach this code because
all these functions are invoked by ggml_compute_forward_dup
if and only if src0->type != dst->type

Signed-off-by: Salvatore Mesoraca <[email protected]>

* Make ggml_compute_forward_dup_same_cont work with contiguous tensors

Co-authored-by: Georgi Gerganov <[email protected]>
Signed-off-by: Salvatore Mesoraca <[email protected]>

---------

Signed-off-by: Salvatore Mesoraca <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>
* enable Ascend NPU in src/whisper.cpp
  * sync test-backend-ops with llama.cpp
* tests: add gradient checking to test-backend-ops

* remove old comment

* reorder includes

* adjust SIN/COS parameters

* add documentation, use supports_op if possible
test-backend-ops fails because ggml_cont aborts
when invoked passing an unsupported type.

This commit makes ggml_cont tests pass

Signed-off-by: Salvatore Mesoraca <[email protected]>
sin and cos failed test-backend-ops because they
tried to dereference a context pointer that is null
on dry runs.

This commit prevents that segfault.

Signed-off-by: Salvatore Mesoraca <[email protected]>
@ggerganov ggerganov merged commit a876861 into master Sep 8, 2024
53 checks passed
@ggerganov ggerganov deleted the sync branch September 8, 2024 08:05
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs script Script related testing Everything test related Vulkan Issues specific to the Vulkan backend
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants