Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model: LFM2-VL fixes (#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
2025-11-30 21:57:31 +01:00
committed by GitHub
parent 7f8ef50cce
commit 2ba719519d
12 changed files with 162 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-device.m
+1 -1
View File
@@ -894,7 +894,7 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
case GGML_OP_POOL_1D:
return false;
case GGML_OP_UPSCALE:
return op->src[0]->type == GGML_TYPE_F32 && op->op_params[0] == GGML_SCALE_MODE_NEAREST;
return op->src[0]->type == GGML_TYPE_F32 && op->op_params[0] == GGML_SCALE_MODE_NEAREST && !(op->op_params[0] & GGML_SCALE_FLAG_ANTIALIAS);
case GGML_OP_POOL_2D:
return op->src[0]->type == GGML_TYPE_F32;
case GGML_OP_PAD: