Skip to content

models : dedup qwen35 graphs #19660

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ggerganov merged 2 commits into from
Feb 19, 2026
Merged

models : dedup qwen35 graphs #19660

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3f6ca46
models : dedup qwen35 graphs
ggerganov Feb 16, 2026
1f5a7e4
cont : add missing sigmoid
ggerganov Feb 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 2 additions & 56 deletions src/models/models.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -542,8 +542,7 @@ struct llm_build_qwen3next : public llm_build_delta_net_base {
const llama_model & model;
};

// TODO: derive llm_build_delta_net_base instead
struct llm_build_qwen35 : public llm_graph_context {
struct llm_build_qwen35 : public llm_build_delta_net_base {
llm_build_qwen35(const llama_model & model, const llm_graph_params & params);
private:
ggml_tensor * build_layer_attn(
Expand All @@ -556,39 +555,12 @@ struct llm_build_qwen35 : public llm_graph_context {
ggml_tensor * build_layer_attn_linear(
llm_graph_input_rs * inp,
ggml_tensor * cur,
ggml_tensor * causal_mask,
ggml_tensor * identity,
ggml_tensor * diag_mask,
int il);


ggml_tensor * build_layer_ffn(
ggml_tensor * cur,
int il);

// returns pair of output and new state
std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_chunking(
ggml_tensor * q,
ggml_tensor * k,
ggml_tensor * v,
ggml_tensor * g,
ggml_tensor * beta,
ggml_tensor * state,
ggml_tensor * causal_mask,
ggml_tensor * identity,
ggml_tensor * diag_mask,
int il);

// returns pair of output and new state
std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_autoregressive(
ggml_tensor * q,
ggml_tensor * k,
ggml_tensor * v,
ggml_tensor * g,
ggml_tensor * beta,
ggml_tensor * state,
int il);

ggml_tensor * build_norm_gated(
ggml_tensor * input,
ggml_tensor * weights,
Expand All @@ -604,7 +576,7 @@ struct llm_build_qwen35 : public llm_graph_context {
};

// TODO: derive llm_build_delta_net_base instead
struct llm_build_qwen35moe : public llm_graph_context {
struct llm_build_qwen35moe : public llm_build_delta_net_base {
llm_build_qwen35moe(const llama_model & model, const llm_graph_params & params);
private:
ggml_tensor * build_layer_attn(
Expand All @@ -617,38 +589,12 @@ struct llm_build_qwen35moe : public llm_graph_context {
ggml_tensor * build_layer_attn_linear(
llm_graph_input_rs * inp,
ggml_tensor * cur,
ggml_tensor * causal_mask,
ggml_tensor * identity,
ggml_tensor * diag_mask,
int il);

ggml_tensor * build_layer_ffn(
ggml_tensor * cur,
int il);

// returns pair of output and new state
std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_chunking(
ggml_tensor * q,
ggml_tensor * k,
ggml_tensor * v,
ggml_tensor * g,
ggml_tensor * beta,
ggml_tensor * state,
ggml_tensor * causal_mask,
ggml_tensor * identity,
ggml_tensor * diag_mask,
int il);

// returns pair of output and new state
std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_autoregressive(
ggml_tensor * q,
ggml_tensor * k,
ggml_tensor * v,
ggml_tensor * g,
ggml_tensor * beta,
ggml_tensor * state,
int il);

ggml_tensor * build_norm_gated(
ggml_tensor * input,
ggml_tensor * weights,
Expand Down
Loading
Loading