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

model : support NVFP4 tensors for Gemma4 (#21971)

Browse Source 
* support nvfp4 tensors for Gemma4

* add wo_s to build_attn

* add wo_s to build_attn

* fix glm4
This commit is contained in:
Sigbjørn Skjæret
2026-04-16 16:51:47 +02:00
committed by GitHub
parent b572d1ecd6
commit f772f6e434
105 changed files with 149 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/kimi-linear.cpp
+2 -2
View File
@@ -268,7 +268,7 @@ llm_build_kimi_linear::llm_build_kimi_linear(const llama_model & model, const ll
ggml_tensor * Vcur = kv_cmpr;
cb(Vcur, "Vcur", il);
cur = build_attn(inp_attn_k, layer.wo, NULL, Qcur, Kcur, Vcur, nullptr, nullptr, layer.wv_b, kq_scale_mla, il);
cur = build_attn(inp_attn_k, layer.wo, NULL, layer.wo_s, Qcur, Kcur, Vcur, nullptr, nullptr, layer.wv_b, kq_scale_mla, il);
cb(cur, "mla_out", il);
} else { // MLA KV cache disabled. Fall back to MHA KV cache.
Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head_k_mla, n_head, n_tokens);
@@ -299,7 +299,7 @@ llm_build_kimi_linear::llm_build_kimi_linear(const llama_model & model, const ll
// Direct softmax attention (with MHA KV cache)
// Use build_attn with inp_attn for proper mask handling
cur = build_attn(inp_attn_kv, layer.wo, NULL, Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale_mla, il);
cur = build_attn(inp_attn_kv, layer.wo, NULL, layer.wo_s, Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale_mla, il);
cb(cur, "mla_out", il);
}
}