Pikaliov
71862bbeca
- Add dcnv4_int8_cuda.cu/.h: CUDA kernel (int8 values, fp16 offsets, fp32 interp, requantize with value_scale/output_scale) - Add dcnv4_int8_forward(): inference-only functional wrapper (@no_grad) - Add DCNv4Strip.forward_int8(): module-level INT8 forward (without_pointwise=True) - Add scripts/test_dcnv4_int8.py: correctness gate (<=1 LSB, >=99% exact) and informational fp16 vs int8 benchmark - Update README: INT8 API section, updated structure tree, SOFIA/MERIDIAN context Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
11 lines
727 B
Python
11 lines
727 B
Python
# ------------------------------------------------------------------------------------------------
|
|
# Deformable DETR
|
|
# Copyright (c) 2020 SenseTime. All Rights Reserved.
|
|
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
|
|
# ------------------------------------------------------------------------------------------------
|
|
# Modified from https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch/tree/pytorch_1.0.0
|
|
# ------------------------------------------------------------------------------------------------
|
|
|
|
# from .ms_flash_deform_attn_func import FlashMSDeformAttnFunction
|
|
from .flash_deform_attn_func import FlashDeformAttnFunction
|
|
from .dcnv4_func import DCNv4Function, dcnv4_int8_forward |