From 50703d3c3a6f2e964542912a173a20b4be21a03d Mon Sep 17 00:00:00 2001 From: Niko Maroulis Date: Wed, 7 Oct 2026 09:41:50 -0400 Subject: [PATCH] metal : fix MUL_MAT+ADD fusion when the residual is itself a MUL_MAT (llama/30100) * metal : fix MUL_MAT+ADD fusion when the residual is itself a MUL_MAT ggml_metal_op_mul_mat_mma picks the residual of a fused MUL_MAT+ADD as "the ADD operand whose op is not MUL_MAT". When both operands of the ADD are mat-mul outputs (x = W1 @ u + W2 @ v), that test is true for both, so the residual resolves to the fused mat-mul's own, never-written output and the kernel adds whatever that buffer holds. The fusion check (ggml_metal_mul_mat_add_operand) already selects the operand by identity; make the encoder do the same. Clef decision models hit this in their head (proj_option_context @ ctx + proj_option_lexical @ lex, 9 option rows): on Metal, /v1/systemone probabilities collapse toward uniform (billing 0.28 where the CPU backend gives 0.977, Cloudflare_clef-flash Q8_0), deterministic per memory layout, correct with GGML_METAL_FUSION_DISABLE=1. Not a quantization issue: the same file is right on CPU. Add a MUL_MAT_ADD mode to test-backend-ops where the residual is a second mat-mul; on Metal it fails 27 of 28 cases before this change (the one pass is f16 n=2, under the MMA row threshold, so nothing fuses). * Update tests/test-backend-ops.cpp Co-authored-by: Georgi Gerganov --------- Co-authored-by: Georgi Gerganov --- ggml/src/ggml-metal/ggml-metal-ops.cpp | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/ggml/src/ggml-metal/ggml-metal-ops.cpp b/ggml/src/ggml-metal/ggml-metal-ops.cpp index 2a14cd0c2..597d5300c 100644 --- a/ggml/src/ggml-metal/ggml-metal-ops.cpp +++ b/ggml/src/ggml-metal/ggml-metal-ops.cpp @@ -2476,7 +2476,8 @@ static int ggml_metal_op_mul_mat_mma(ggml_metal_op_t ctx, int idx) { if (fuse_add) { dst = ctx->node(idx + n_fuse - 1); - res = dst->src[0]->op == GGML_OP_MUL_MAT ? dst->src[1] : dst->src[0]; + // the residual is the other operand of the ADD, by identity: it can itself be a MUL_MAT output + res = dst->src[0] == op ? dst->src[1] : dst->src[0]; } auto pipeline = ggml_metal_library_get_pipeline_mul_mv_mma_auto(lib, op, fuse_add);