fix: Allow batch encoding and remove clip_is_idefics3

Branch: GraniteDocling

Signed-off-by: Gabe Goodhart <[email protected]>

Author: gabe-l-hart

tools/mtmd/clip.cpp

@@ -4426,10 +4426,6 @@ bool clip_is_gemma3(const struct clip_ctx * ctx) {
     return ctx->proj_type() == PROJECTOR_TYPE_GEMMA3;
 }
 
-bool clip_is_idefics3(const struct clip_ctx * ctx) {
-    return ctx->proj_type() == PROJECTOR_TYPE_IDEFICS3;
-}
-
 bool clip_has_vision_encoder(const struct clip_ctx * ctx) {
     return ctx->model.modality == CLIP_MODALITY_VISION;
 }

tools/mtmd/clip.h

@@ -95,7 +95,6 @@ bool clip_is_glm(const struct clip_ctx * ctx);
 bool clip_is_qwen2vl(const struct clip_ctx * ctx);
 bool clip_is_llava(const struct clip_ctx * ctx);
 bool clip_is_gemma3(const struct clip_ctx * ctx);
-bool clip_is_idefics3(const struct clip_ctx * ctx);
 
 bool clip_encode_float_image (struct clip_ctx * ctx, int n_threads, float * img, int h, int w, float * vec);
 

tools/mtmd/mtmd.cpp

@@ -796,8 +796,7 @@ int32_t mtmd_encode(mtmd_context * ctx, const mtmd_image_tokens * image_tokens)
 
     if (clip_is_llava(ctx_clip)
         || clip_is_minicpmv(ctx_clip)
-        || clip_is_glm(ctx_clip)
-        || clip_is_idefics3(ctx_clip)) {
+        || clip_is_glm(ctx_clip)) {
         // TODO @ngxson : llava does not support batched encoding ; this should be fixed inside clip_image_batch_encode()
         const auto & entries = image_tokens->batch_f32.entries;
         for (size_t i = 0; i < entries.size(); i++) {