Ascend NPU Ring-SP Performance (Wan2.1-T2V-1.3B)

• Baseline config: ulysses=1, ring=1 (short: u1r1)
• Ring-SP config: ulysses=1, ring=2 (short: u1r2)

​

Benchmark Setup

• Model: Wan2.1-T2V-1.3B-Diffusers
• Prompt: "a cat is playing piano"
• Framework command: sglang generate
• Runtime: torch_npu==2.10.0

​

Generate Commands

​

Baseline (u1r1)

sglang generate --model-path /nas/disk1/Wan2.1-T2V-1.3B-Diffusers \
    --prompt "a cat is playing piano" --num-gpus 1 --ring-degree 1 \
    --save-output

​

Ring-SP (u1r2)

sglang generate --model-path /nas/disk1/Wan2.1-T2V-1.3B-Diffusers \
    --prompt "a cat is playing piano" --num-gpus 2 --ring-degree 2 \
    --save-output

​

Benchmarks

​

Stage Time Breakdown

​

Summary

• With torch_npu==2.10.0, Ring-SP (u1r2) runs successfully on NPU for this case.
• End-to-end generation time improves from 266.50s to 141.86s (1.88x).
• The main gain comes from DenoisingStage (1.97x), while decoding also improves (1.19x).