From dd36d62a04adcd5ee1ec377b79833fbe682af52e Mon Sep 17 00:00:00 2001 From: bong-water-water-bong Date: Fri, 13 Nov 2026 23:00:19 -0400 Subject: [PATCH] tests: fa_prefill_full_cache.512 is a known-fail, and the label names the defect (engine#2374 item 3) The case asserts a compact F16 mask alternate and an initialization dispatch named `qwen3_moe:qwen_attention_metadata`. Neither exists in this tree, and I measured it on BOTH paths: with the HIP add-on [FAIL] compact_mask != nullptr :2394 GGML_HRX_DISABLE_DISPATCH=hip. (Loom path) [FAIL] compact_mask != nullptr :2394 Same assertion both times, and `:2394` runs BEFORE the case looks for any flash dispatch. So this is not an add-on matcher claiming a node whose Loom-path plan the case asserts -- the failure shape llama.cpp#355 fixes for hrx-backend-test. It is a real, path-independent absence: * no `append_alternate_value` caller publishes a `GGML_TYPE_F16` alternate (the F16 mentions near alternates are `find_alternate_value` lookups, in dispatch-routed-ffn.cpp:394 and :881); * `grep -rln qwen_attention_metadata ggml/src/ggml-hrx/` returns nothing, so no dispatch can carry that name. `testing_suite.h` has had `known_fail_device_case` since engine#449 (llama.cpp#353 added it to this runner), so the case is labelled rather than left red or deleted. **The label names the DEFECT, not the issue**: engine#2374 will close, and a label pointing at a closed issue gets deleted by whoever tidies up, taking the case's meaning with it. Named this way, the day a compact F16 mask alternate is published the case reports `[UNEXPECTED-PASS]` and removes itself. Measured after the change, one gpu-hold window (1145 ms, coder-llm restored, :8090=200, no amdgpu reset and no amdxdna fault before or after): [KNOWN-FAIL] 1/1 fa_prefill_full_cache.512 test-hrx-ops summary: 0 passed, 0 failed, 1 known-fail, 0 unexpected-pass, 1 total rc=0 The reason is printed even when it passes this way, which is the point: a green suite must not read as "the case passes". --- tests/test-hrx-ops.cpp | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/tests/test-hrx-ops.cpp b/tests/test-hrx-ops.cpp index 79c0f87e93b6..1d3947a922a1 100644 --- a/tests/test-hrx-ops.cpp +++ b/tests/test-hrx-ops.cpp @@ -6630,8 +6630,18 @@ static void add_cases(test_runner::Suite & suite) { [=] { run_qwen_decode_attention_output_next_q8_scheduling_case(false); }); add(suite, "fa_decode_next_q8.true", [=] { run_qwen_decode_attention_output_next_q8_scheduling_case(true); }); - add(suite, "fa_prefill_full_cache.512", - [=] { run_qwen_full_cache_prefill_flash_attention_scheduling_case(512); }); + // engine#2374 item 3: measured on BOTH paths -- with the HIP add-on and with GGML_HRX_DISABLE_DISPATCH=hip. + // Both fail at the same assertion, `compact_mask != nullptr` (test-hrx-ops.cpp:2394), which runs BEFORE the + // case looks for any flash dispatch. So this is not an add-on claiming a Loom-path node: no + // append_alternate_value caller publishes a GGML_TYPE_F16 alternate anywhere in the tree, and the + // `qwen3_moe:qwen_attention_metadata` dispatch the case also waits for is not registered at all + // (`grep -rln qwen_attention_metadata ggml/src/ggml-hrx/` returns nothing). The compact-mask optimisation + // this case was written for does not exist on this line; the label names the DEFECT rather than the issue, + // so the day a compact F16 mask alternate is published this becomes an UNEXPECTED-PASS and gets removed. + suite.known_fail_device_case("fa_prefill_full_cache.512", + "engine#2374 item 3: no compact F16 mask alternate is published (and no " + "qwen_attention_metadata dispatch exists) on either the add-on or the Loom path", + [=] { run_qwen_full_cache_prefill_flash_attention_scheduling_case(512); }); } int main(int argc, char ** argv) {