sleepy/llama.cpp
1
0
Fork 0
Code Issues 16 Pull Requests Actions 137 Packages Projects Releases Wiki Activity

TP: fix Qwen 3 Next data split (#21732)

Browse Source
This commit is contained in:
Johannes Gäßler
2026-04-11 09:23:42 +02:00
committed by GitHub
parent 2b2cd57de6
commit 865ff06b2f
2 changed files with 39 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/qwen3next.cpp
+2 -2
View File
@@ -354,7 +354,7 @@ ggml_tensor * llm_build_qwen3next::build_layer_attn_linear(
cb(last_conv_states, "last_conv_states", il);
ggml_tensor * state_update_target =
ggml_view_1d(ctx0, conv_states_all, (conv_kernel_size - 1) * conv_channels * n_seqs,
ggml_view_2d(ctx0, conv_states_all, (conv_kernel_size - 1) * conv_channels, n_seqs, conv_states_all->nb[1],
kv_head * (conv_kernel_size - 1) * conv_channels * ggml_element_size(conv_states_all));
cb(state_update_target, "state_update_target", il);
@@ -445,7 +445,7 @@ ggml_tensor * llm_build_qwen3next::build_layer_attn_linear(
// Update the recurrent states
ggml_build_forward_expand(gf,
ggml_cpy(ctx0, new_state,
ggml_view_1d(ctx0, ssm_states_all, hparams.n_embd_s() * n_seqs,
ggml_view_2d(ctx0, ssm_states_all, hparams.n_embd_s(), n_seqs, ssm_states_all->nb[1],
kv_head * hparams.n_embd_s() * ggml_element_size(ssm_states_all))));
// z: [head_dim, n_heads, n_tokens, n_seqs] -> [n_heads * n_tokens * n_seqs, head_dim]