Replace the copy+merge_adapter pair in refresh_lora_merge_from_pristine
with one torch.addmm(pristine, B, A, alpha=scaling, out=W_inf) per
LoraLayer, then set merged_adapters directly so PEFT's forward
short-circuits to base_layer(x).
Previously each refresh did two passes per weight: a bf16 copy from
pristine, then PEFT merge_adapter which materialises a full [out, in]
fp32 delta via get_delta_weight and in-place adds it back. The fused
path skips the transient delta allocation and runs one cuBLAS GEMM
instead. cuBLAS accumulates the bf16 matmul in fp32 internally, so the
numerical result stays within 1 bf16 ULP of PEFT's path (verified on
the rank-32 Qwen3-4B adapter: max abs diff 1.22e-04).
DoRA, fan_in_fan_out, and lora_bias=True layers fall back to PEFT's
get_delta_weight/merge path via a single trailing merge_adapter call
after restoring their base_layer.weight from pristine. rslora is not a
fallback -- PEFT folds alpha/sqrt(r) into module.scaling[adapter], so
the fused addmm picks it up transparently via alpha=.
Drift verification still passes: base bit-identical across 10
perturb+refresh cycles, inference state deterministic after LoRA
restore.
314ab6ae86