diff --git a/single_shot_inference.py b/single_shot_inference.py index 4a37cae7..a355ba1d 100644 --- a/single_shot_inference.py +++ b/single_shot_inference.py @@ -1841,7 +1841,7 @@ def main(): # Run full attention eagerly (compressor + indexer + FMHA + o_proj) F_attn, _ = forward_attention( x_normed, layer_w[li], li, cfg, *rope_caches[gpu], - kv_caches[li], dec_pos_per_gpu[gpu], dec_tid32_per_gpu[gpu], + kv_caches[li], dec_pos_per_gpu[gpu], compressors.get(li), indexers.get(li), prod_lins.get(li), q_heads=q_heads, kv_3d=kv_3d, # pass pre-computed q/kv from graph A comp_rope_cos=comp_rope_caches[gpu][0] if comp_rope_caches else None,