Early return for zero size calls to get_tensor. #5482
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Adam Treat <[email protected]>
ggerganov
approved these changes
Feb 13, 2024
|
It would also be ok to do this more generally in ggml-backend so that all backends benefit from it. |
Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>
Signed-off-by: Adam Treat <[email protected]>
|
See also abde521 |
cebtenzzre
reviewed
Feb 13, 2024
Signed-off-by: Adam Treat <[email protected]>
…do so here as well. Signed-off-by: Adam Treat <[email protected]>
slaren
approved these changes
Feb 13, 2024
cebtenzzre
pushed a commit
to nomic-ai/llama.cpp
that referenced
this pull request
Feb 13, 2024
* Early return for zero size calls to get_tensor. Signed-off-by: Adam Treat <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Add an early return to the get/set tensor when the size is null. Signed-off-by: Adam Treat <[email protected]> * Early return after the assertions. Signed-off-by: Adam Treat <[email protected]> * Since we do the early return in the generic backend now no reason to do so here as well. Signed-off-by: Adam Treat <[email protected]> --------- Signed-off-by: Adam Treat <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
jordankanter
pushed a commit
to jordankanter/llama.cpp
that referenced
this pull request
Mar 13, 2024
* Early return for zero size calls to get_tensor. Signed-off-by: Adam Treat <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Add an early return to the get/set tensor when the size is null. Signed-off-by: Adam Treat <[email protected]> * Early return after the assertions. Signed-off-by: Adam Treat <[email protected]> * Since we do the early return in the generic backend now no reason to do so here as well. Signed-off-by: Adam Treat <[email protected]> --------- Signed-off-by: Adam Treat <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
hodlen
pushed a commit
to hodlen/llama.cpp
that referenced
this pull request
Apr 1, 2024
* Early return for zero size calls to get_tensor. Signed-off-by: Adam Treat <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Add an early return to the get/set tensor when the size is null. Signed-off-by: Adam Treat <[email protected]> * Early return after the assertions. Signed-off-by: Adam Treat <[email protected]> * Since we do the early return in the generic backend now no reason to do so here as well. Signed-off-by: Adam Treat <[email protected]> --------- Signed-off-by: Adam Treat <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The llama_copy_state_data_internal function can sometimes call ggml_backend_tensor_get with a null size when the kv cache is empty. This guards against unnecessarily syncing from device to host in such a case.