[Test] Add e2e test and accuracy test for Qwen3-Next-80B-A3B-Instruct (#3450)
### What this PR does / why we need it? Add e2e test and accuracy test for Qwen3-Next-80B-A3B-Instruct ### How was this patch tested? accuracy test: https://github.com/vllm-project/vllm-ascend/actions/runs/18771221544/job/53556027634?pr=3450 ci test: https://github.com/vllm-project/vllm-ascend/actions/runs/18771221530/job/53556027614?pr=3450 <img width="1703" height="562" alt="image" src="https://github.com/user-attachments/assets/973b6cfa-8240-41e3-893a-5024ff8d0693" /> - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
15
tests/e2e/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
Normal file
15
tests/e2e/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
Normal file
@@ -0,0 +1,15 @@
|
||||
model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct"
|
||||
hardware: "Atlas A2 Series"
|
||||
model: "vllm"
|
||||
tasks:
|
||||
- name: "ceval-valid_accountant"
|
||||
metrics:
|
||||
- name: "acc,none"
|
||||
value: 0.98
|
||||
max_model_len: 4096
|
||||
tensor_parallel_size: 4
|
||||
gpu_memory_utilization: 0.7
|
||||
enable_expert_parallel: True
|
||||
enforce_eager: True
|
||||
batch_size: 1
|
||||
num_fewshot: 5
|
||||
Reference in New Issue
Block a user