-
Please make sure that this is a feature request. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature …
-
Hi, I tried a test about compiling unet(torch.float16), which is the part of StableDiffusionXLPipeline in Inferentia2.8xlarge and it failed.
When the latent size of unet is (64, 64), it did not fai…
-
While it is very nice to see that float16 values (e.g., as object attributes) are finally supported since 3.3.2, unfortunately float16 datasets are not supported yet.
Example code to create a malic…
-
Since ISPC 1.17, we have `float16` type (IEEE 754 [half precision](https://en.wikipedia.org/wiki/Half-precision_floating-point_format) type), which is now native ISPC type. This means that it should b…
-
On my system, which doesn't have native `Float16`, the method for `rounding(Float16)` doesn't exist. As far as I see effectively the rounding mode is `RoundNearest`, no? So I guess the method should b…
-
**Description**
runtime error during normal usage.
**System info:**
- Filediver version: 0.3.3
- OS: Windows
**Error output**
Only include errors that actually pertain to the described type …
-
Quark is a comprehensive cross-platform toolkit designed to simplify and enhance the quantization of deep learning models. Supporting both PyTorch and ONNX models, Quark empowers developers to optimiz…
-
I'm going to do several experiments around distillation data decoding, and it will be easier to write up the results here as they are all related to the same part of the pipeline, `translate-mono-src`…
-
Using HDF5 to read data stored as 16-bit floating point into a 32-bit buffer is extremely slow, around 16x slower than an equivalent conversion in numpy. I uploaded a demo [here](https://github.com/bh…
-
### Problem description
Hi there,
Is there any plan to add support for float16, I recently run into a situation where I have to optimize the memory footprint of my dataframe to some extreme due …