Skip to content

Optimization: Qwen3 next autoregressive pass #17996

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
pwilkin merged 6 commits into from
Dec 16, 2025
+86 −271
Merged

Optimization: Qwen3 next autoregressive pass #17996

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b739b11
It's Qwen3 Next, the lean mean token generation machine!
pwilkin Dec 13, 2025
bd7b710
Apply patches from thread
pwilkin Dec 15, 2025
9357f6d
Remove recurrent version, only keep chunked and autoregressive
pwilkin Dec 15, 2025
a58f2ac
Remove unnecessary conts and asserts
pwilkin Dec 15, 2025
2c44d21
Remove more extra conts and asserts
pwilkin Dec 15, 2025
b1477de
Cleanup masking
pwilkin Dec 16, 2025
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
10 changes: 5 additions & 5 deletions src/models/models.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -441,13 +441,14 @@ struct llm_build_qwen3next : public llm_graph_context_mamba {
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);

ggml_tensor * build_delta_net_recurrent(
ggml_tensor * build_delta_net_chunking(
ggml_tensor * q,
ggml_tensor * k,
ggml_tensor * v,
Expand All @@ -456,18 +457,17 @@ struct llm_build_qwen3next : public llm_graph_context_mamba {
ggml_tensor * state,
ggml_tensor * causal_mask,
ggml_tensor * identity,
ggml_tensor * diag_mask,
int il);

ggml_tensor * build_delta_net_chunking(
ggml_tensor * build_delta_net_autoregressive(
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,
int il);
int il);

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