Jiejing Zhang

Change quandl example from WIKI to EOD.

3

quandl already not update WIKI source anymore. Please change exmaple to EOD, which can fetch the latest prices. Received this from Quandl Support April 11, 2018: I'm emailing you because...

Bi-Direction forward and backward seems incorrect, only capture half of input_x in each direction in element-wise

3

Hi Tao, I recently found there is issue in bi-direction case, such as input_size = 6, hidden_size = 3, direction_count = 2, length = 2, batch_size = 2 in this...

About Grad: gradient check failed in some case, how to correct calculate x's gradient ?

6

Hi Taolei, In you sru implement, the backward step will update a grad_u matrix, but in many framework like tensorflow, the grad operation will only rqeuire to calc the input...

Could you explain how to get grad_w and grad_x from grad_u?

3

Hi Musyoku, I'm implementing SRU in tensorflow with a accelrated implement, I have finished the forward part referening taolei87's code, but I have trouble implementing the gradient part, in taolei87's...

ROIAlign Interpolating is incorrect

1

Hi, Recently I found the ROIAlign in roi_align_op_gpu.cu.cc will have incorrect interpolation value in some conner case. the case is like this, when the h or w passed to ROIAlignGetInterpolating()...

Could you provide a more complex example like a larger gemm (more than 16x64, like 1024x1024) to show how to use change the load tile register while moving through different...

Add Support for mac armv9 support, with A16W8 quantization.

1

- need port to mac (M4 + ) ARMv9 - disable openMP (because default xcode clang not support openMP) - enable a16w8 quantization support to reduce RAM requirement.

fastapi support refinement.

TRT Support for Qwen2.5VL Error.

6

Code : `3945858be258c95656fdeabcaf56413b35dd368e` Test method: `dashinfer_vlm_serve --model Qwen2.5-VL-3B-Instruct --host 127.0.0.1 --vision_engine tensorrt` Version: ``` transformers 4.54.0 torch 2.7.1 torchvision 0.22.1 onnx 1.18.0 tensorrt 10.5.0 tensorrt-cu12 10.13.0.35 tensorrt-cu12-bindings 10.13.0.35 tensorrt-cu12-libs 10.13.0.35...