model : wire up Nemotron-H tensors for NVFP4 support (#20561)
* wire up Nemotron-H tensors for NVFP4 support * add ssm tensors * alignment
This commit is contained in:
@@ -7501,6 +7501,9 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
|
||||
}
|
||||
|
||||
// recurrent / linear-attention weight scales (per-tensor, shape {1})
|
||||
if (!layer.ssm_in_s && layer.ssm_in) {
|
||||
layer.ssm_in_s = create_tensor(tn(LLM_TENSOR_SSM_IN, "scale", i), {1}, TENSOR_NOT_REQUIRED);
|
||||
}
|
||||
if (!layer.ssm_out_s && layer.ssm_out) {
|
||||
layer.ssm_out_s = create_tensor(tn(LLM_TENSOR_SSM_OUT, "scale", i), {1}, TENSOR_NOT_REQUIRED);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user