public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-18 13:17:59 +02:00
Code Issues Packages Projects Releases Wiki Activity

model: LFM2-VL fixes (llama/17577)

Browse Source 
* Adjust to pytorch

* Add antialiasing upscale

* Increase number of patches to 1024

* Handle default marker insertion for LFM2

* Switch to flag

* Reformat

* Cuda implementation of antialias kernel

* Change placement in ops.cpp

* consistent float literals

* Pad only for LFM2

* Address PR feedback

* Rollback default marker placement changes

* Fallback to CPU implementation for antialias implementation of upscale
This commit is contained in:
Tarek Dakhran
2025-12-12 17:53:14 +02:00
committed by Georgi Gerganov
parent 706647202e
commit 0defeee679
9 changed files with 149 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-vulkan/ggml-vulkan.cpp
+1
View File
@@ -14113,6 +14113,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
}
return true;
case GGML_OP_UPSCALE:
return op->src[0]->type == GGML_TYPE_F32 && !(op->op_params[0] & GGML_SCALE_FLAG_ANTIALIAS);
case GGML_OP_ACC:
return op->src[0]->type == GGML_TYPE_F32;
case GGML_OP_CONCAT: