diff --git a/.github/workflows/_base_test.yml b/.github/workflows/_base_test.yml index 859e60d32ce..27e03f07b0a 100644 --- a/.github/workflows/_base_test.yml +++ b/.github/workflows/_base_test.yml @@ -40,7 +40,7 @@ jobs: workflow-name: base_test base_tests: - runs-on: [self-hosted, GPU-h20-1Cards] + runs-on: [self-hosted, GPU-h20-New-Driver] needs: check_bypass if: ${{ inputs.FASTDEPLOY_WHEEL_URL != '' && needs.check_bypass.outputs.can-skip != 'true' }} timeout-minutes: 60 diff --git a/.github/workflows/_build_linux.yml b/.github/workflows/_build_linux.yml index 1431df353cb..90bedf33aa4 100644 --- a/.github/workflows/_build_linux.yml +++ b/.github/workflows/_build_linux.yml @@ -70,7 +70,7 @@ jobs: workflow-name: build_gpu fd-build: - runs-on: [self-hosted, GPU-Build] + runs-on: [self-hosted, GPU-Build-New-Driver] needs: check_bypass if: ${{ needs.check_bypass.outputs.can-skip != 'true' }} timeout-minutes: 360 diff --git a/.github/workflows/_logprob_test_linux.yml b/.github/workflows/_logprob_test_linux.yml index 0a014d26854..9c9816ffbf1 100644 --- a/.github/workflows/_logprob_test_linux.yml +++ b/.github/workflows/_logprob_test_linux.yml @@ -41,7 +41,7 @@ jobs: workflow-name: logprob_test run_tests_logprob: - runs-on: [self-hosted, GPU-h20-1Cards] + runs-on: [self-hosted, GPU-h20-New-Driver] needs: check_bypass if: ${{ inputs.FASTDEPLOY_WHEEL_URL != '' && needs.check_bypass.outputs.can-skip != 'true' }} timeout-minutes: 60 diff --git a/.github/workflows/_pre_ce_test.yml b/.github/workflows/_pre_ce_test.yml index 8c5e20e2de0..0627ab97d23 100644 --- a/.github/workflows/_pre_ce_test.yml +++ b/.github/workflows/_pre_ce_test.yml @@ -39,7 +39,7 @@ jobs: workflow-name: pre_ce_test run_ce_cases: - runs-on: [self-hosted, PRE_CE_RUN_2Card] + runs-on: [self-hosted, GPU-h20-New-Driver] needs: check_bypass if: ${{ inputs.FASTDEPLOY_WHEEL_URL != '' && needs.check_bypass.outputs.can-skip != 'true' }} timeout-minutes: 60 diff --git a/.github/workflows/_stable_test.yml b/.github/workflows/_stable_test.yml index e37d0c4fe6b..15d2a86d3ca 100644 --- a/.github/workflows/_stable_test.yml +++ b/.github/workflows/_stable_test.yml @@ -40,7 +40,7 @@ jobs: workflow-name: stable_test stable_tests: - runs-on: [self-hosted, GPU-h20-2Cards] + runs-on: [self-hosted, GPU-h20-New-Driver] needs: check_bypass if: ${{ inputs.FASTDEPLOY_WHEEL_URL != '' && needs.check_bypass.outputs.can-skip != 'true' }} timeout-minutes: 60 diff --git a/.github/workflows/_unit_test_coverage.yml b/.github/workflows/_unit_test_coverage.yml index a7603e6d1e5..1178a7d073d 100644 --- a/.github/workflows/_unit_test_coverage.yml +++ b/.github/workflows/_unit_test_coverage.yml @@ -40,7 +40,7 @@ jobs: workflow-name: coverage run_tests_with_coverage: - runs-on: [self-hosted, GPU-h1z1-2Cards] + runs-on: [self-hosted, GPU-h20-New-Driver] timeout-minutes: 105 needs: check_cov_skip if: ${{ inputs.FASTDEPLOY_WHEEL_URL != '' && needs.check_cov_skip.outputs.can-skip != 'true' }} diff --git a/tests/layers/test_plas_attention.py b/tests/layers/test_plas_attention.py index e593595fa5a..98dfb4bb72c 100644 --- a/tests/layers/test_plas_attention.py +++ b/tests/layers/test_plas_attention.py @@ -101,7 +101,9 @@ def setUp(self): [self.tokens + self.attn_block_m, self.num_kv_heads, self.head_dim], dtype="bfloat16", ) - self.rotary_embs = paddle.ones([2, self.seq_len, self.head_dim // 2], dtype="float32") + rotary_cos = paddle.ones([1, self.plas_max_seq_length, self.head_dim // 2], dtype="float32") + rotary_sin = paddle.zeros([1, self.plas_max_seq_length, self.head_dim // 2], dtype="float32") + self.rotary_embs = paddle.concat([rotary_cos, rotary_sin], axis=0) self.attn_gate_weight = paddle.randn( [self.num_kv_heads, self.plas_block_size, self.head_dim], dtype="bfloat16"