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

model: support GLM MoE DSA arch (NOTE: indexer is not yet supported) (#19460)

Browse Source 
* model: support GLM MoE DSA arch

* working version

* pyright

* keep indexer tensors

* add indexer gguf params

* loaded now

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* update

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* minor fix and cleanup

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Xuan-Son Nguyen
2026-02-13 14:56:53 +01:00
committed by GitHub
co-authored by Sigbjørn Skjæret
parent cc2aa81513
commit 752584d5f5
10 changed files with 361 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.h
+8
View File
@@ -130,6 +130,7 @@ enum llm_type {
LLM_TYPE_300B_A47B, // Ernie MoE big
LLM_TYPE_310B_A15B, // /MiMo-V2-Flash
LLM_TYPE_355B_A32B, // GLM-4.5
LLM_TYPE_744B_A40B, // GLM-5
LLM_TYPE_E2B,
LLM_TYPE_E4B,
};
@@ -429,6 +430,13 @@ struct llama_layer {
struct ggml_tensor * ssm_g_b = nullptr;
struct ggml_tensor * ssm_o_norm = nullptr;
// DSA (deepseek sparse attention)
struct ggml_tensor * indexer_k_norm = nullptr;
struct ggml_tensor * indexer_k_norm_b = nullptr;
struct ggml_tensor * indexer_proj = nullptr;
struct ggml_tensor * indexer_attn_k = nullptr;
struct ggml_tensor * indexer_attn_q_b = nullptr; // note: for lora a/b, not bias
struct llama_layer_posnet posnet;
struct llama_layer_convnext convnext;