add google magika inference example #748
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
Would this patch make it work with the F16 GELU define? diff --git a/src/ggml.c b/src/ggml.c
index d710fe7..42a7d45 100644
--- a/src/ggml.c
+++ b/src/ggml.c
@@ -1560,9 +1560,15 @@ inline static void ggml_vec_gelu_f16(const int n, ggml_fp16_t * y, const ggml_fp
inline static void ggml_vec_gelu_f32(const int n, float * y, const float * x) {
uint16_t t;
for (int i = 0; i < n; ++i) {
- ggml_fp16_t fp16 = GGML_FP32_TO_FP16(x[i]);
- memcpy(&t, &fp16, sizeof(uint16_t));
- y[i] = GGML_FP16_TO_FP32(ggml_table_gelu_f16[t]);
+ if (x[i] < -10.0f) {
+ y[i] = 0.0f;
+ } else if (x[i] > 10.0f) {
+ y[i] = x[i];
+ } else {
+ ggml_fp16_t fp16 = GGML_FP32_TO_FP16(x[i]);
+ memcpy(&t, &fp16, sizeof(uint16_t));
+ y[i] = GGML_FP16_TO_FP32(ggml_table_gelu_f16[t]);
+ }
}
}
#else |
|
Yep, it does work. The problem was that activations generated by this model can exceed the FP16 maximum finite value of 65519, which results in |
ggerganov
reviewed
Feb 25, 2024
ggerganov
approved these changes
Feb 25, 2024
|
CUDA does not support POOL_1D either, so I guess it is CPU only for now. |
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Outdated suggestions cannot be applied.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 model can be converted with
convert.pyfrom model.h5Example: