minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Push test case scripts from test repo to main upstream community repository (#31114)

Browse Source
This commit is contained in:
pllimax
2026-07-16 21:24:01 +08:00
committed by GitHub
parent 7d0fd5101d
commit 4ad418d2c3
14 changed files with 541 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/nightly-test-npu-e2e-single-node.yml
+2
View File
@@ -164,6 +164,8 @@ jobs:
source /usr/local/Ascend/cann/set_env.sh || true
source /usr/local/Ascend/nnal/atb/set_env.sh || true
source /usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/bin/set_env.bash || true
source /usr/local/Ascend/ascend-toolkit/latest/opp/vendors/custom_transformer/bin/set_env.bash || true
# Set environment of cann
log_path="/root/.cache/tests/logs/log/${current_date}/${tc_name}/${HOSTNAME}"
.github/workflows/nightly-test-npu.yml
+20 -4
View File
@@ -239,10 +239,6 @@ jobs:
- name: glm4_7_flash_1p_aime25
runner: linux-aarch64-a3-2
test_case: test/registered/ascend/accuracy/glm4_7_flash/test_npu_glm4_7_flash_1p_aime25.py
# glm4_6v_flash accuracy tests
- name: glm4_6v_flash_1p_mmmu
runner: linux-aarch64-a3-2
test_case: test/registered/ascend/accuracy/glm4_6v_flash/test_npu_glm4_6v_flash_1p_mmmu.py
# qwen3_vl_8b_thinking accuracy tests
- name: qwen3_vl_8b_thinking_1p_mmmu
runner: linux-aarch64-a3-2
@@ -251,6 +247,11 @@ jobs:
- name: qwen3_vl_30b_a3b_thinking_1p_mmmu
runner: linux-aarch64-a3-2
test_case: test/registered/ascend/accuracy/qwen3_vl_30b_a3b_thinking/test_npu_qwen3_vl_30b_a3b_thinking_1p_mmmu.py
# deepseek_v4_flash performance tests
- name: deepseek_v4_flash_w8a8_8p_in8k_out1k_50ms
runner: linux-aarch64-a3-16
test_case: test/registered/ascend/performance/deepseek_v4_flash/test_npu_deepseek_v4_flash_w8a8_8p_in8k_out1k_50ms.py
test_type: 'perf'
uses: ./.github/workflows/nightly-test-npu-e2e-single-node.yml
with:
runner: ${{ matrix.test_config.runner }}
@@ -278,6 +279,21 @@ jobs:
test_case: test/registered/ascend/performance/glm5_1/test_npu_glm5_1_w4a8_1p1d_32p_in64k_out1k_50ms_aime26.py
test_type: 'perf'
prefill_decode_deployment: 'separation'
# mimo_v2_flash performance tests
- name: test_npu_mimo_v2_flash_1p1d_12p_in16k_out1_ttft_5s
prefill_size: 1
decode_size: 1
router_size: 1
test_case: test/registered/ascend/performance/mimo_v2_flash/test_npu_mimo_v2_flash_1p1d_12p_in16k_out1_ttft_5s.py
test_type: 'perf'
prefill_decode_deployment: 'separation'
- name: test_npu_mimo_v2_flash_1p1d_12p_in16k_out1k_tpot_20ms
prefill_size: 1
decode_size: 1
router_size: 1
test_case: test/registered/ascend/performance/mimo_v2_flash/test_npu_mimo_v2_flash_1p1d_12p_in16k_out1k_tpot_20ms.py
test_type: 'perf'
prefill_decode_deployment: 'separation'
uses: ./.github/workflows/nightly-test-npu-e2e-multi-node.yml
with:
runner: linux-amd64-cpu-8