xc-llm-ascend

Files

SILONG ZENG 09b3f9d91b [CI]Add Disaggregated PD Nightly Test for Qwen3-235B and Qwen3-VL-235B (#5502 )

### What this PR does / why we need it?
This PR adds online **Disaggregated Prefill/Decode** performance and
accuracy tests for the **Qwen3-235B-A22B** and
**Qwen3-VL-235B-A22B-Instruct** models to the Nightly test suite.

These test configurations simulate the deployment of massive MoE and
Vision-Language models in **a dual-node (32 NPU)** environment,
utilizing Mooncake (KVCache Transfer) technology to achieve efficient KV
cache transfer between the Prefill node and the Decode node.

#### Test Configuration
**Qwen3-235B-A22B**
- Model: Qwen/Qwen3-235B-A22B
- Hardware: A3, 2 Nodes (32 NPUs total, 16 NPUs per node)
- Architecture: Disaggregated Prefill & Decode
- Node 0 (Producer/Prefill): **DP2 + TP8 + EP + FLASHCOMM1 +
FUSED_MC2**.
- Node 1 (Consumer/Decode): **DP4 + TP4 + EP + FLASHCOMM1 + FUSED_MC2 +
FULL_DECODE_ONLY**.
- Benchmarks:
  - Performance: vllm-ascend/GSM8K-in3500-bs2800.
  - Accuracy: vllm-ascend/gsm8k-lite.

**Qwen3-VL-235B-A22B-Instruct**
- Model: Qwen/Qwen3-VL-235B-A22B-Instruct
- Hardware: A3, 2 Nodes (32 NPUs total, 16 NPUs per node)
- Architecture: Disaggregated Prefill & Decode
  - Node 0 (Producer/Prefill): **DP2 + TP8 + EP**.
  - Node 1 (Consumer/Decode): **DP4 + TP4 + EP + FULL_DECODE_ONLY**.
- Benchmarks:
  - Performance: vllm-ascend/textvqa-perf-1080p.
  - Accuracy: vllm-ascend/textvqa-lite.

### How was this patch tested?
Nightly test action on CI

- vLLM version: v0.13.0
- vLLM main:
45c1ca1ca1

---------

Signed-off-by: MrZ20 <2609716663@qq.com>

2026-01-09 16:25:20 +08:00

DeepSeek-R1-W8A8-A2.yaml

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

2025-12-30 19:03:02 +08:00

DeepSeek-R1-W8A8-EPLB.yaml

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

2025-12-30 19:03:02 +08:00

DeepSeek-R1-W8A8-longseq.yaml

[BugFix] Fix Smoke Testing Bug for DSR1 longseq (#5613 )

2026-01-05 22:40:28 +08:00

DeepSeek-R1-W8A8.yaml

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