From c01c26b56e06384b9410a11a9afbf2c13d285a05 Mon Sep 17 00:00:00 2001
From: Millaguie <javi@millaguie.net>
Date: Mon, 10 Aug 2026 23:09:23 +0200
Subject: [PATCH] tests : skip test-dt3-gpu on backends that do not implement
 DT3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The test picked the first GPU device it found and treated an unsupported
op as a failure. Vulkan and SYCL answer supports_op == false for DT3,
which is the right answer for them and not a bug to report, so the test
went red on machines that were behaving correctly. Metal is worse: it
answers true for almost any type but has no DT3 shader, so the run died
in pipeline compilation halfway through.

Pick the backend by name instead — CUDA and HIP (which reports itself as
ROCm) are the only ones implementing DT3 — and skip everything else. A
supports_op failure on those two is still a real failure.

Also document that the n <= 8 gating mirrors MMVQ_MAX_BATCH_SIZE by hand
and goes stale silently if the MMVQ dispatch changes.
---
 tests/test-dt3-gpu.cpp | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/tests/test-dt3-gpu.cpp b/tests/test-dt3-gpu.cpp
index 19e7f28c6..703024533 100644
--- a/tests/test-dt3-gpu.cpp
+++ b/tests/test-dt3-gpu.cpp
@@ -33,7 +33,8 @@
 // random bytes: every byte value 0..255 must decode identically on both
 // sides, including values >= 243 that never come out of the packer.
 //
-// Without a GPU backend the test is skipped and succeeds.
+// DT3 is implemented for CUDA and HIP only. Without one of those backends the
+// test is skipped and succeeds — an unsupported backend is not a failure.
 
 #include "ggml.h"
 #include "ggml-alloc.h"
@@ -324,6 +325,13 @@ static int test_mul_mat(ggml_backend_t backend, ggml_type type, const std::vecto
         // hardware and on GGML_CUDA_CUBLAS_COMPUTE_TYPE) are cuBLAS's, not
         // ours: for the strict type it is gated below by bit-identity with
         // the same GEMM on an F16 tensor, and only reported here.
+        // This mirrors MMVQ_MAX_BATCH_SIZE (8) from ggml-cuda/mmvq.cu by hand,
+        // because the constant and the per-arch should_use_mmvq tables are not
+        // exported. If upstream raises the limit, or an architecture routes a
+        // larger batch through MMVQ, this gating goes stale silently: n = 16
+        // would take the MMVQ path but still be judged as the GEMM one, which
+        // only loosens the check, never tightens it. Whoever touches the MMVQ
+        // dispatch should revisit this line.
         const bool   is_mmvq = n <= 8;
         const bool   gated   = is_mmvq || !strict;
         const double err_gate = is_mmvq ? err.norm_rel : (err.norm_rel < err16.norm_rel ? err.norm_rel : err16.norm_rel);
@@ -453,17 +461,29 @@ static void build_control_data(ggml_type type, std::vector<uint8_t> & data, std:
 }
 
 int main(void) {
+    // Only CUDA and HIP (which reports itself as "ROCm") implement DT3. Any
+    // other GPU backend is skipped rather than failed: Vulkan and SYCL answer
+    // supports_op == false for DT3, which is the correct answer for them and
+    // not a bug to report, and Metal answers true for almost any type but has
+    // no DT3 shader, so it would die in pipeline compilation mid-test. Picking
+    // the backend by name keeps this test honest on machines we do not have.
     ggml_backend_t backend = nullptr;
     for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
         ggml_backend_dev_t dev = ggml_backend_dev_get(i);
-        if (ggml_backend_dev_type(dev) == GGML_BACKEND_DEVICE_TYPE_GPU) {
-            backend = ggml_backend_dev_init(dev, nullptr);
-            printf("using GPU backend: %s\n", ggml_backend_dev_name(dev));
-            break;
+        if (ggml_backend_dev_type(dev) != GGML_BACKEND_DEVICE_TYPE_GPU) {
+            continue;
         }
+        const char * name = ggml_backend_dev_name(dev);
+        if (strncmp(name, "CUDA", 4) != 0 && strncmp(name, "ROCm", 4) != 0) {
+            printf("skipping GPU backend %s: DT3 is only implemented for CUDA/HIP\n", name);
+            continue;
+        }
+        backend = ggml_backend_dev_init(dev, nullptr);
+        printf("using GPU backend: %s\n", name);
+        break;
     }
     if (backend == nullptr) {
-        printf("no GPU backend available, skipping\n");
+        printf("no CUDA/HIP backend available, skipping\n");
         return 0;
     }