nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 17 Packages Projects Releases Wiki Activity

mtp: support for gemma-4 E2B and E4B assistants (#24282)

Browse Source 
* models: update converter to support smaller assistants

* models: add masked_embd tensors to gemma4-assist arch

* gemma-4: remove temp debug for conversion

* gemma-4-mtp: filter out masked_embedding tensors during conversion
This commit is contained in:
Max Krasnyansky
2026-06-08 13:48:52 -07:00
committed by GitHub
parent 42a0afd594
commit 7d2b45b4f7
6 changed files with 34 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
+4
View File
@@ -559,6 +559,8 @@ static const std::map<llm_tensor, const char *> LLM_TENSOR_NAMES = {
{ LLM_TENSOR_INDEXER_PROJ, "blk.%d.indexer.proj" },
{ LLM_TENSOR_INDEXER_ATTN_K, "blk.%d.indexer.attn_k" },
{ LLM_TENSOR_INDEXER_ATTN_Q_B, "blk.%d.indexer.attn_q_b" },
{ LLM_TENSOR_MASKED_EMBD_CENTROIDS, "masked_embd_centroids" },
{ LLM_TENSOR_MASKED_EMBD_ORDERING, "masked_embd_ordering" },
};
// declare information about the model weight tensors:
@@ -783,6 +785,8 @@ static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
// latent projections feed ggml_mul_mat, the buft probe must use MUL_MAT to keep them on GPU
{LLM_TENSOR_FFN_LATENT_DOWN, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
{LLM_TENSOR_FFN_LATENT_UP, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
{LLM_TENSOR_MASKED_EMBD_CENTROIDS, {LLM_TENSOR_LAYER_INPUT, GGML_OP_NONE}},
{LLM_TENSOR_MASKED_EMBD_ORDERING, {LLM_TENSOR_LAYER_INPUT, GGML_OP_NONE}},
};
LLM_KV::LLM_KV(llm_arch arch, const char * suffix) : arch(arch), suffix(suffix) {}
src/llama-arch.h
+3
View File
@@ -566,8 +566,11 @@ enum llm_tensor {
LLM_TENSOR_NEXTN_HNORM,
LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD,
LLM_TENSOR_NEXTN_SHARED_HEAD_NORM,
LLM_TENSOR_MASKED_EMBD_CENTROIDS,
LLM_TENSOR_MASKED_EMBD_ORDERING,
};
enum llm_tensor_layer {
LLM_TENSOR_LAYER_INPUT,
LLM_TENSOR_LAYER_REPEATING,
src/models/gemma4-assistant.cpp
+3
View File
@@ -39,6 +39,9 @@ void llama_model_gemma4_assistant::load_arch_tensors(llama_model_loader &) {
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0);
create_tensor(tn(LLM_TENSOR_MASKED_EMBD_CENTROIDS, "weight"), {}, TENSOR_NOT_REQUIRED);
create_tensor(tn(LLM_TENSOR_MASKED_EMBD_ORDERING), {}, TENSOR_NOT_REQUIRED);
const int64_t n_embd_backbone = hparams.n_embd_inp();
nextn_proj_post = create_tensor(tn(LLM_TENSOR_NEXTN_PROJ_POST, "weight"), { n_embd, n_embd_backbone }, 0);