Fix Qwen3Next CI Config (#7561)

### What this PR does / why we need it?
This pr modifies qwen3Next nightly CI config. 
(1) Add a nightly CI .
(2) Set a more precise accuracy standard

- vLLM version: v0.18.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209

Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
This commit is contained in:
LeeWenquanandYour Name authored and GitHub committed 2026-03-24 17:08:17 +08:00
1 parent d98a0727c8
commit 9615bc33fd
4 files changed
+13 -8

No files matched your search

@@ -282,6 +282,9 @@ jobs:
- name: qwen3-30b-a3b-w8a8
os: linux-aarch64-a3-4
config_file_path: Qwen3-30B-A3B-W8A8.yaml
- name: qwen3-next-80b-a3b-instruct
os: linux-aarch64-a3-4
config_file_path: Qwen3-Next-80B-A3B-Instruct.yaml
- name: qwen3-next-80b-a3b-instruct-w8a8
os: linux-aarch64-a3-4
config_file_path: Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
@@ -24,6 +24,8 @@ _server_cmd: &server_cmd
- "0.8"
- "--max-num-seqs"
- "64"
- "--compilation_config"
- '{"cudagraph_mode": "FULL_DECODE_ONLY"}'
_benchmarks: &benchmarks
perf:
@@ -44,8 +46,8 @@ _benchmarks: &benchmarks
max_out_len: 32768
batch_size: 32
top_k: 20
baseline: 95
threshold: 5
baseline: 96
threshold: 3
# ==========================================
# ACTUAL TEST CASES
@@ -41,5 +41,5 @@ test_cases:
dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
max_out_len: 32768
batch_size: 32
baseline: 95
threshold: 5
baseline: 96
threshold: 3
@@ -24,8 +24,8 @@ _server_cmd: &server_cmd
- "0.8"
- "--max-num-seqs"
- "64"
- "--compilation-config"
- '{"cudagraph_capture_sizes": [64]}'
- "--compilation_config"
- '{"cudagraph_mode": "FULL_DECODE_ONLY"}'
_benchmarks: &benchmarks
perf:
@@ -46,8 +46,8 @@ _benchmarks: &benchmarks
max_out_len: 32768
batch_size: 64
top_k: 20
baseline: 95
threshold: 5
baseline: 96
threshold: 3
# ==========================================
# ACTUAL TEST CASES