tests : add GQA=20 FA test (#19095)

diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index d4c1f525c674c5cead70cb6b0983da0672696753..411467e968f43c0270e3c888efe00339f63a2f6f 100644 (file)
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -8213,11 +8213,13 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
                         if (!mask && max_bias > 0.0f) continue;
                         for (float logit_softcap : {0.0f, 10.0f}) {
                             if (hsk != 128 && logit_softcap != 0.0f) continue;
-                            for (int nh : { 4, }) {
+                            for (int nh : { 1, 4 }) {
+                                if (nh == 1 && hsk != 576) continue; // GLM 4.7 Flash
                                 for (int nr3 : { 1, 3, }) {
                                     if (hsk > 64 && nr3 > 1) continue; // skip broadcast for large head sizes
-                                    for (int nr2 : { 1, 4, 12 }) {
+                                    for (int nr2 : { 1, 4, 12, 20 }) {
                                         if (nr2 == 12 && hsk != 128) continue;
+                                        if (nr2 == 20 && (nh != 1 || hsk != 576)) continue;
                                         //for (int kv : { 1, 17, 31, 33, 61, 113, 65, 127, 129, 130, 255, 260, 371, 380, 407, 512, 1024, }) {
                                         for (int kv : { 113, 512, 1024, }) {
                                             if (nr2 != 1 && kv != 512) continue;