Cherry_mingandSugar920 1eb40d8d45 [NPU]Optimize the PR pipeline to reduce E2E runtime (#18767) ...

Co-authored-by: Sugar920 <121632458+Sugar920@users.noreply.github.com>

2026-02-28 17:06:03 +08:00

..

ascend

[NPU]Optimize the PR pipeline to reduce E2E runtime (#18767)

2026-02-28 17:06:03 +08:00

configs

…

cpu

…

models

…

xpu

…

double-sparsity-config-Llama-3.1-8B-Instruct.json

…

experiment_runner.py

…

kv_cache_scales_llama3_1_8b.json

…

kv_cache_scales_llama3_8b.json

…

kv_cache_scales_qwen2_1_5b.json

…

parse_results.py

…

run_suite.py

[NPU]Optimize the PR pipeline to reduce E2E runtime (#18767)

2026-02-28 17:06:03 +08:00

test_embed_interpolate_unittest.py

…