Skip to content
Merged
Changes from all commits
Commits
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: 10 additions & 0 deletions npu/forward/src/q4nx_forward.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -3023,6 +3023,16 @@ void Q4nxNpuForward::npu_gemm_rows(int role, const float* A, int M, int K, int N

// The folded container's sign table: magic "HAD1", u32 count, count x (u32 width, u32 offset),
// then the f32 signs those offsets index (the GGUF's prism.hadamard.sign_widths/sign_values).
// The plain-text overload. It is declared in q4nx_forward.h and used by npu/forward/embeds_equiv_probe.cpp, but only the
// HybridInputs-taking definition existed, so every full build stopped at `undefined reference to
// Q4nxNpuForward::step_batch_embeds(std::vector<float>, int, std::vector<float>&)` — the onebit target links because it
// does not pull the probe in, which is why the breakage survived a release-ish build. Defaulting `in` is exactly the
// documented meaning of the three-argument form: no position planes, no deepstack sets, nothing vision-conditioned.
bool Q4nxNpuForward::step_batch_embeds(const std::vector<float>& embeds, int start_pos,
std::vector<float>& logits) {
return step_batch_embeds(embeds, start_pos, logits, HybridInputs{});
}

bool Q4nxNpuForward::step_batch_embeds(const std::vector<float>& embeds, int start_pos,
std::vector<float>& logits, const HybridInputs& in) {
if (!ready_) { err_ = "not initialised"; return false; }
Expand Down
Loading