[E2E] Optimize nightly testcase. (#4886)
### What this PR does / why we need it?
Optimize nightly testcase.
Changes:
- tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A3B.yaml: Add
accuracy and performance benchmark
- tests/e2e/models/configs/Qwen3-8B-Base.yaml: Delete
- tests/e2e/models/configs/internlm-7b.yaml: Change to
internlm3-8b-instruct
- tests/e2e/nightly/models/test_deepseek_r1_w8a8_eplb.py: Change to
DeepSeek-R1-0528-W8A8 model
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: menogrey <1299267905@qq.com>
This commit is contained in:
13
tests/e2e/models/configs/internlm3-8b-instruct.yaml
Normal file
13
tests/e2e/models/configs/internlm3-8b-instruct.yaml
Normal file
@@ -0,0 +1,13 @@
|
||||
model_name: "Shanghai_AI_Laboratory/internlm3-8b-instruct"
|
||||
hardware: "Atlas A2 Series"
|
||||
tasks:
|
||||
- name: "ceval-valid"
|
||||
metrics:
|
||||
- name: "acc,none"
|
||||
value: 0.42
|
||||
num_fewshot: 5
|
||||
max_model_len: 2048
|
||||
trust_remote_code: True
|
||||
dtype: "bfloat16"
|
||||
apply_chat_template: False
|
||||
fewshot_as_multiturn: False
|
||||
Reference in New Issue
Block a user