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

[SYCL] Add TIMESTEP_EMBEDDING OP #8707

Merged
merged 2 commits into from
Jul 30, 2024
Merged

Conversation

zhentaoyu
Copy link
Contributor

Add SYCL TIMESTEP_EMBEDDING operator by following the related CUDA kernel.
temporary solution to support SYCL backend for stablediffusion.cpp leejet/stable-diffusion.cpp#308

@airMeng airMeng requested review from airMeng and joeatodd July 26, 2024 08:57
@github-actions github-actions bot added ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language labels Jul 26, 2024
@airMeng
Copy link
Collaborator

airMeng commented Jul 29, 2024

ggerganov/ggml#900 please add t5 layernorm using this PR too

@zhentaoyu
Copy link
Contributor Author

ggerganov/ggml#900 please add t5 layernorm using this PR too

Will add them in another PR. Thanks.

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>
@zhentaoyu
Copy link
Contributor Author

rebased. @luoyu-intel please take a look. Thanks.

ggml/src/ggml-sycl/tsembd.cpp Outdated Show resolved Hide resolved
Signed-off-by: zhentaoyu <zhentao.yu@intel.com>
@airMeng airMeng requested a review from luoyu-intel July 30, 2024 06:09
@airMeng airMeng merged commit c887d8b into ggerganov:master Jul 30, 2024
53 checks passed
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Aug 2, 2024
Signed-off-by: zhentaoyu <zhentao.yu@intel.com>
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 SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants