-
- CPU architecture: x86_64
- GPU: NVIDIA H100
- Libraries
- TensorRT-LLM: v0.11.0
- TensorRT: 10.1.0
- Modelopt: 0.13.1
- CUDA: 12.3
- NVIDIA driver version: 535.129.03
Hello, I'm e…
-
Since Ada GPUs like 4090 limit the FP8 arithmetic into `fp32` accumulation, it only achieve the same max `TFLOPs` compared to `fp16xfp16` with `fp16` accumulation.
Further more, according to my test,…
-
Hi,
I try to add Qwen-moe into mixtral_moe.py, and I have done some modifications. But now, I meet some problems in there.
![1](https://github.com/cg123/mergekit/assets/53638291/000d5134-0fe0-4ba5-…
-
Dear Authors,
Thank you for your works. May I ask why we need up and down variables in the model?
-
### Proposal
Add Llama 3.1 support. Currently trying to load it fails with:
`ValueError: meta-llama/Meta-Llama-3.1-8B-Instruct not found. Valid official model names (excl aliases): `
### Mot…
-
> Taxonomic assignment is the core of targeted metagenomics approaches that aims to assign sequencing reads to their corresponding taxonomy. Sequence similarity searching and machine learning (ML) are…
-
Updates from:
- https://github.com/jacobhilton/deep_learning_curriculum (focus on transformers)
- Raschka book
1. Math prerequisites
Taking a derivative to find a point of minimum or maxim…
-
Add a module for MLP neural network for pressure interpolation at different angles of attack
-
In tensorflow I just do this for weights clipping:
t_vars = tf.trainable_variables()
critic_vars = [var for var in t_vars if 'crit' in var.name]
self.clip_critic = []
for var in critic_vars:
…
-
I just modify the model by
model = actnn.QModule(model)
After that, something wrong happened as follows:
Traceback (most recent call last):
File "train.py", line 336, in
main()
F…