deepseekv4.1: follow-up review fixes (#31137)
* kv-cache : use ggml_backend_tensor_copy to refill the DSV4 K mirrors * llama : move the Engram pad id to llama_hparams and the token map to llama_model The saver no longer needs the deepseek41 model class. * deepseek41 : drop the F32 src1 request on the HC mixes matmul * ggml : add softplus TODOs in the backends that still use log(1 + exp(x)) * convert : make the DSV4/DSV4.1 modify_tensors generators, drop the redundant vision filter * deepseek41 : clean up comments * deepseek41 : drop the F32 src1 requests on the router and indexer matmuls * convert : use format_tensor_name directly in DeepseekV4Model * s/comp_kv_src/comp_il_src/g * cont : fix TODOs for log1p --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
1 parent
d854d98bae
commit
a074215352
12 files changed
+59
-93
No files matched your search
@@ -1406,7 +1406,7 @@ llama_model_dflash::graph_dsv41::graph_dsv41(const llama_model & model, const ll
|
||||
ggml_tensor * post = nullptr;
|
||||
ggml_tensor * comb = nullptr;
|
||||
|
||||
ggml_tensor * attn_pre = build_hc_mixes(inpL, layer.hc_attn_fn, layer.hc_attn_scale, layer.hc_attn_base, &post, &comb, false, il);
|
||||
ggml_tensor * attn_pre = build_hc_mixes(inpL, layer.hc_attn_fn, layer.hc_attn_scale, layer.hc_attn_base, &post, &comb, il);
|
||||
|
||||
ggml_tensor * cur;
|
||||
if (pre_prev == nullptr) {
|
||||
@@ -1465,7 +1465,7 @@ llama_model_dflash::graph_dsv41::graph_dsv41(const llama_model & model, const ll
|
||||
cb(inpL, "hc_attn_post", il);
|
||||
|
||||
residual = inpL;
|
||||
ggml_tensor * ffn_pre = build_hc_mixes(inpL, layer.hc_ffn_fn, layer.hc_ffn_scale, layer.hc_ffn_base, &post, &comb, false, il);
|
||||
ggml_tensor * ffn_pre = build_hc_mixes(inpL, layer.hc_ffn_fn, layer.hc_ffn_scale, layer.hc_ffn_base, &post, &comb, il);
|
||||
|
||||
cur = build_hc_pre(inpL, attn_pre, il);
|
||||
cb(cur, "hc_ffn_pre", il);
|
||||
|
||||
Reference in new issue
Block a user