From b3337e1c65cc82efcb221315328f2f6fabc8da01 Mon Sep 17 00:00:00 2001 From: gasoonjia Date: Sun, 11 Oct 2026 19:03:52 -0700 Subject: [PATCH] [cuda] Move the large-M quantized GEMM suites out of unittest-cuda too unittest-cuda is cancelled at its 90-minute timeout on every recent main commit. #23605 moved the quantized GEMM kernel suites into unittest-cuda-quantized-gemm, but the same push added test_int4_large_quantized_gemm.py (~7.7 min on the A10G) and test_int6_large_quantized_gemm.py (~5.1 min), which still run in unittest-cuda. On #23635 its backends/cuda/tests pytest alone took 62 min and the job was cancelled during the Gemma 4 tests that follow. Run both in the second quantized-GEMM shard, renamed large-int5-int6-int8-graph-timing (that shard took 44 min; the int4 shard already takes ~60). unittest-cuda ignores them. No test is dropped. --- .github/workflows/cuda.yml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/.github/workflows/cuda.yml b/.github/workflows/cuda.yml index a5b863fba0e..28f31a8373d 100644 --- a/.github/workflows/cuda.yml +++ b/.github/workflows/cuda.yml @@ -540,8 +540,10 @@ jobs: # job's timeout. python -m pytest backends/cuda/tests backends/cuda/passes/tests -v -o "addopts=" \ --ignore=backends/cuda/tests/test_int4_quantized_gemm.py \ + --ignore=backends/cuda/tests/test_int4_large_quantized_gemm.py \ --ignore=backends/cuda/tests/test_int5_quantized_gemm.py \ --ignore=backends/cuda/tests/test_int6_quantized_gemm.py \ + --ignore=backends/cuda/tests/test_int6_large_quantized_gemm.py \ --ignore=backends/cuda/tests/test_int8_quantized_gemm.py \ --ignore=backends/cuda/tests/test_cuda_graph_timing.py @@ -566,10 +568,13 @@ jobs: include: - shard: int4 tests: backends/cuda/tests/test_int4_quantized_gemm.py - - shard: int5-int6-int8-graph-timing + # The int4 shard alone takes ~60 min, so the large-M suites go here. + - shard: large-int5-int6-int8-graph-timing tests: >- + backends/cuda/tests/test_int4_large_quantized_gemm.py backends/cuda/tests/test_int5_quantized_gemm.py backends/cuda/tests/test_int6_quantized_gemm.py + backends/cuda/tests/test_int6_large_quantized_gemm.py backends/cuda/tests/test_int8_quantized_gemm.py backends/cuda/tests/test_cuda_graph_timing.py uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main