sync : ggml (ggml_scale, ggml_row_size, etc.) #1677
Merged
Conversation
This file contains 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
ggerganov
commented
Dec 22, 2023
| @@ -449,11 +449,10 @@ static void init_view(ggml_gallocr_t galloc, struct ggml_tensor * view, bool upd | |||
| if (update_backend) { | |||
| view->backend = view->view_src->backend; | |||
| } | |||
| view->buffer = view->view_src->buffer; | |||
| // views are initialized in the alloc buffer rather than the view_src buffer | |||
| view->buffer = alloc->buffer; | |||
There was a problem hiding this comment.
@slaren After the sync, the following command produces incorrect transcription:
make samples
make -j && ./main -m ./models/ggml-medium.en.bin -f ./samples/gb0.wavReverting just this line fixes the issue. Any guess what this could be related to?
Maybe something is incompatible with the whisper_allocr_graph_realloc logic
There was a problem hiding this comment.
I think it is because this change interferes with auto-inline logic. This should fix it:
diff --git a/ggml-alloc.c b/ggml-alloc.c
index a97436b..a27dd54 100644
--- a/ggml-alloc.c
+++ b/ggml-alloc.c
@@ -72,7 +72,7 @@ static void remove_allocated_tensor(ggml_tallocr_t alloc, struct ggml_tensor * t
// check if a tensor is allocated by this buffer
static bool ggml_tallocr_is_own(ggml_tallocr_t alloc, const struct ggml_tensor * tensor) {
- return tensor->buffer == alloc->buffer;
+ return tensor->buffer == alloc->buffer && (!tensor->view_src || tensor->view_src->buffer == alloc->buffer);
}
static bool ggml_is_view(struct ggml_tensor * t) {
bygreencn
added a commit
to bygreencn/whisper.cpp
that referenced
this pull request
Dec 25, 2023
* ggerganov/master: whisper : Replace WHISPER_PRINT_DEBUG with WHISPER_LOG_DEBUG (ggerganov#1681) sync : ggml (ggml_scale, ggml_row_size, etc.) (ggerganov#1677) docker : Dockerize whisper.cpp (ggerganov#1674) CI : Add coverage for talk-llama when WHISPER_CUBLAS=1 (ggerganov#1672) examples : Revert CMakeLists.txt for talk-llama (ggerganov#1669) cmake : set default CUDA architectures (ggerganov#1667)
viktor-silakov
pushed a commit
to viktor-silakov/whisper_node_mic.cpp
that referenced
this pull request
May 11, 2024
* sync : ggml * sync : llama.cpp * talk-llama : fix obsolete param * ggml-alloc : fix ggml_tallocr_is_own * talk.wasm : update to new ggml * ggml : fix type punning in ggml_scale * ggml : cuda jetson + arm quants warnings
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.
No description provided.