From 9615bc33fda0d62d6eadfb79ae58efd0fb4fb597 Mon Sep 17 00:00:00 2001
From: LeeWenquan <83354342+SunnyLee151064@users.noreply.github.com>
Date: Tue, 24 Mar 2026 17:08:17 +0800
Subject: [PATCH] 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>
---
 .github/workflows/schedule_nightly_test_a3.yaml           | 3 +++
 .../models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml    | 6 ++++--
 .../models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml  | 4 ++--
 .../models/configs/Qwen3-Next-80B-A3B-Instruct.yaml       | 8 ++++----
 4 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/.github/workflows/schedule_nightly_test_a3.yaml b/.github/workflows/schedule_nightly_test_a3.yaml
index 885c0854..e2ada87f 100644
--- a/.github/workflows/schedule_nightly_test_a3.yaml
+++ b/.github/workflows/schedule_nightly_test_a3.yaml
@@ -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
diff --git a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml
index 56a653fe..0d9f1452 100644
--- a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.yaml
+++ b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-A2.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
diff --git a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
index 3deddc75..cd47eef4 100644
--- a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
+++ b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
@@ -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
diff --git a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
index fc126efa..02b03bdd 100644
--- a/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
+++ b/tests/e2e/nightly/single_node/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
@@ -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