Skip to content

Conversation

@lhez
Copy link
Collaborator

@lhez lhez commented Feb 12, 2025

Properly identify mark multi rope and vision rope and mark them as unsupported so that these rope variants get put back to CPU and does not crash. Also fp16 variant of soft_max is added.

@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Feb 12, 2025
@lhez lhez marked this pull request as ready for review February 13, 2025 01:01
@max-krasnyansky max-krasnyansky merged commit 300907b into ggml-org:master Feb 14, 2025
43 of 46 checks passed
orca-zhang pushed a commit to orca-zhang/llama.cpp that referenced this pull request Feb 26, 2025
* opencl: fix `ROPE`

* opencl: fix `SOFT_MAX`

* Add fp16 variant

* opencl: enforce subgroup size for `soft_max`
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Feb 26, 2025
* opencl: fix `ROPE`

* opencl: fix `SOFT_MAX`

* Add fp16 variant

* opencl: enforce subgroup size for `soft_max`
mglambda pushed a commit to mglambda/llama.cpp that referenced this pull request Mar 8, 2025
* opencl: fix `ROPE`

* opencl: fix `SOFT_MAX`

* Add fp16 variant

* opencl: enforce subgroup size for `soft_max`
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

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants