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

..

_test_utils

Reduce diffusers example-test compute with tiny models

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

examples

Use minimum TensorRT build optimization in diffusers tests

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

gpu

Fix NVFP4 fake quant zeroing blocks with small scales (#2549)

2026-09-29 10:31:31 -07:00

gpu_megatron

Fix grouped expert quantizer checkpoint replicas (#2500)

2026-09-24 20:01:56 +00:00

gpu_trtllm

Fix 2-GPU test_model_load_utils hang; test import and fixture cleanup (#2079)

2026-08-05 21:00:42 +05:30

gpu_vllm

[1/n] Adds skip-softmax calibration through the vLLM serving path (#1992)

2026-09-18 12:31:10 -07:00

regression/torch/speculative

Speed up slow unit/gpu/example tests (#1616)

2026-06-04 17:13:10 +00:00

unit

Use minimum TensorRT build optimization in diffusers tests

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

conftest.py

[1/2] One MLflow tracking core behind a Tool record (#2544)

2026-09-28 19:57:03 +00:00