ajrasane 4826fb7554 Use minimum TensorRT build optimization in diffusers tests ...

Honor explicit builder optimization levels for low-precision and strongly typed engines while preserving existing defaults when omitted. Pass level 0 from every diffusers TensorRT test and cover the override and default behavior.

Signed-off-by: ajrasane <131806219+ajrasane@users.noreply.github.com>

2026-09-29 22:47:01 +00:00

..

assets

Update 0.23.0 - OSS release

2025-01-29 01:45:47 +05:30

calib

Push latest changes

2025-08-26 01:12:26 +05:30

onnx_utils

Reduce diffusers example-test compute with tiny models

2026-09-29 21:41:44 +00:00

.gitignore

Enable torch 2.9 tests in CICD + Diffusers fixes (#561)

2025-11-19 17:11:09 +05:30

build_sdxl_8bit_engine.sh

Push latest changes

2025-08-26 01:12:26 +05:30

calibration.py

Reduce diffusers example-test compute with tiny models

2026-09-29 21:41:44 +00:00

config.py

[5565357] Fix SDXL NVFP4 export and performance (#2336)

2026-09-18 17:22:28 +00:00

diffusion_trt.py

Use minimum TensorRT build optimization in diffusers tests

2026-09-29 22:47:01 +00:00

models_utils.py

Qwen-Image diffusers PTQ: FP8 / NVFP4 / NVFP4-SVDQuant HF checkpoints (#1706)

2026-07-07 17:21:31 -07:00

ONNX-TRT-Deployment.md

[5565357] Fix SDXL NVFP4 export and performance (#2336)

2026-09-18 17:22:28 +00:00

pipeline_manager.py

Qwen-Image diffusers PTQ: FP8 / NVFP4 / NVFP4-SVDQuant HF checkpoints (#1706)

2026-07-07 17:21:31 -07:00

quantize_config.py

[2/3] Implicit Gemm NVFP4 (#1227)

2026-04-19 12:20:14 +05:30

quantize.py

Reduce diffusers example-test compute with tiny models

2026-09-29 21:41:44 +00:00

utils.py

[5565357] Fix SDXL NVFP4 export and performance (#2336)

2026-09-18 17:22:28 +00:00