[1/N] Refactor nightly test structure (#5479)

### What this PR does / why we need it?
This patch is a series of refactoring actions, including clarifying the
directory structure of nightly tests, refactoring the config retrieval
logic, and optimizing the workflow, etc. This is the first step:
refactoring the directory structure of nightly to make it more readable
and logical.

- vLLM version: v0.13.0
- vLLM main:
5326c89803

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-12-30 19:03:02 +08:00
committed by GitHub
parent c85cc045f8
commit e760aae1df
59 changed files with 475 additions and 471 deletions

View File

@@ -51,13 +51,13 @@ jobs:
test_config:
- name: qwen3-32b
os: linux-aarch64-a2-4
tests: tests/e2e/nightly/models/test_qwen3_32b.py
tests: tests/e2e/nightly/single_node/models/test_qwen3_32b.py
- name: qwen3-32b-in8-a2
os: linux-aarch64-a2-4
tests: tests/e2e/nightly/models/test_qwen3_32b_int8.py
tests: tests/e2e/nightly/single_node/models/test_qwen3_32b_int8.py
- name: test_custom_op
os: linux-aarch64-a2-1
tests: tests/e2e/nightly/ops
tests: tests/e2e/nightly/single_node/ops/singlecard_ops
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
with:
vllm: v0.13.0

View File

@@ -56,15 +56,15 @@ jobs:
- name: multi-node-qwen3-dp
config_file_path: Qwen3-235B-A22B.yaml
size: 2
- name: multi-node-dpsk-4node-pd
config_file_path: DeepSeek-R1-W8A8.yaml
size: 4
# - name: multi-node-dpsk-4node-pd
# config_file_path: DeepSeek-R1-W8A8.yaml
# size: 4
- name: multi-node-qwenw8a8-2node
config_file_path: Qwen3-235B-W8A8.yaml
size: 2
- name: multi-node-deepseek-r1-w8a8-eplb
config_file_path: DeepSeek-R1-W8A8-EPLB.yaml
size: 4
# - name: multi-node-deepseek-r1-w8a8-eplb
# config_file_path: DeepSeek-R1-W8A8-EPLB.yaml
# size: 4
- name: multi-node-qwenw8a8-2node-eplb
config_file_path: Qwen3-235B-W8A8-EPLB.yaml
size: 2
@@ -89,47 +89,47 @@ jobs:
test_config:
- name: qwen3-32b-in8-a3
os: linux-aarch64-a3-4
tests: tests/e2e/nightly/models/test_qwen3_32b_int8.py
tests: tests/e2e/nightly/single_node/models/test_qwen3_32b_int8.py
- name: qwen3-32b-int8-a3-feature-stack3
os: linux-aarch64-a3-4
tests: tests/e2e/nightly/features/test_qwen3_32b_int8_a3_feature_stack3.py
tests: tests/e2e/nightly/single_node/models/test_qwen3_32b_int8_a3_feature_stack3.py
- name: qwen3-235b-a22b-w8a8-eplb
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/models/test_qwen3_235b_a22b_w8a8_eplb.py
tests: tests/e2e/nightly/single_node/models/test_qwen3_235b_a22b_w8a8_eplb.py
- name: deepseek-r1-w8a8-eplb
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8_eplb.py
tests: tests/e2e/nightly/single_node/models/test_deepseek_r1_0528_w8a8_eplb.py
- name: deepseek-r1-w8a8-mtpx
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/features/test_mtpx_deepseek_r1_0528_w8a8.py
tests: tests/e2e/nightly/single_node/models/test_mtpx_deepseek_r1_0528_w8a8.py
- name: qwen2-5-vl-7b
os: linux-aarch64-a3-4
tests: tests/e2e/nightly/models/test_qwen2_5_vl_7b.py
tests: tests/e2e/nightly/single_node/models/test_qwen2_5_vl_7b.py
- name: qwen2-5-vl-32b
os: linux-aarch64-a3-4
tests: tests/e2e/nightly/models/test_qwen2_5_vl_32b.py
tests: tests/e2e/nightly/single_node/models/test_qwen2_5_vl_32b.py
- name: qwen3-32b-int8-prefix-cache
os: linux-aarch64-a3-4
tests: tests/e2e/nightly/features/test_prefix_cache_qwen3_32b_int8.py
tests: tests/e2e/nightly/single_node/models/test_prefix_cache_qwen3_32b_int8.py
- name: deepseek-r1-0528-w8a8
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8.py
tests: tests/e2e/nightly/single_node/models/test_deepseek_r1_0528_w8a8.py
- name: deepseek-r1-0528-w8a8-prefix-cache
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/features/test_prefix_cache_deepseek_r1_0528_w8a8.py
tests: tests/e2e/nightly/single_node/models/test_prefix_cache_deepseek_r1_0528_w8a8.py
- name: qwq-32b-a3
os: linux-aarch64-a3-4
tests: tests/e2e/nightly/models/test_qwq_32b.py
tests: tests/e2e/nightly/single_node/models/test_qwq_32b.py
- name: qwen3-30b-w8a8
os: linux-aarch64-a3-2
tests: tests/e2e/nightly/models/test_qwen3_30b_w8a8.py
tests: tests/e2e/nightly/single_node/models/test_qwen3_30b_w8a8.py
- name: qwen3-235b-w8a8
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/models/test_qwen3_235b_w8a8.py
tests: tests/e2e/nightly/single_node/models/test_qwen3_235b_w8a8.py
# TODO: Replace deepseek3.2-exp with deepseek3.2 after nightly tests pass
# - name: deepseek3_2-exp-w8a8
# os: linux-aarch64-a3-16
# tests: tests/e2e/nightly/models/test_deepseek_v3_2_exp_w8a8.py
# tests: tests/e2e/nightly/single_node/models/test_deepseek_v3_2_exp_w8a8.py
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
with:
vllm: v0.13.0
@@ -148,7 +148,7 @@ jobs:
test_config:
- name: custom-op-dispatch_gmm_combine_decode
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/multicard_ops/test_dispatch_gmm_combine_decode.py
tests: tests/e2e/nightly/single_node/ops/multicard_ops/test_dispatch_gmm_combine_decode.py
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
with:
runner: ${{ matrix.test_config.os }}