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

model: Granite Speech Plus (#24818)

Browse Source 
* feat: Add conversion support for Granite Speech Plus

Branch: GraniteSpeechPlus
AI-usage: full (Bob, OpenCode + Qwen3.6-35b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Extend granite_speech to support plus multi-layer concatenation

Branch: GraniteSpeechPlus
AI-usage: draft (Bob, OpenCode + Qwen3.6-35b)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(conversion): Fix plural naming for feature_layers for audio

Branch: GraniteSpeechPlus
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(mtmd): Align feature_layer usage and naming everywhere

Branch: GraniteSpeechPlus
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* style: Use fstring for log

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Gabe Goodhart
2026-06-23 12:03:31 +02:00
committed by GitHub
co-authored by Xuan-Son Nguyen
parent 7c908502ea
commit a3900a6694
10 changed files with 87 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/models/llava.cpp
+3 -3
View File
@@ -21,7 +21,7 @@ ggml_cgraph * clip_graph_llava::build() {
// If we set explicit vision feature layers, only go up to the deepest one
// NOTE: only used by granite-vision models for now
for (const auto & feature_layer : hparams.vision_feature_layer) {
for (const auto & feature_layer : hparams.feature_layers) {
if (feature_layer > deepest_feature_layer) {
deepest_feature_layer = feature_layer;
}
@@ -59,7 +59,7 @@ ggml_cgraph * clip_graph_llava::build() {
// If this is an embedding feature layer, save the output.
// NOTE: 0 index here refers to the input to the encoder.
if (hparams.is_vision_feature_layer(il)) {
if (hparams.is_feature_layer(il)) {
embedding_stack.push_back(cur);
}
@@ -134,7 +134,7 @@ ggml_cgraph * clip_graph_llava::build() {
// process vision feature layers (used by granite)
{
// final layer is a vision feature layer
if (hparams.is_vision_feature_layer(max_feature_layer)) {
if (hparams.is_feature_layer(max_feature_layer)) {
embedding_stack.push_back(inpL);
}