Hao Zhang
Hao Zhang
Hi, I'm trying to test the LinfPGD attack on ImageNet validation set for PyTorch Resnet18. But it seems that the attacks are not throughly successful because the robust accuracy does...
I'm confused whether we need to update the vgg network. The [example](https://github.com/pytorch/examples/tree/master/fast_neural_style) in pytorch tutorial keeps the parameters in vgg16 untouched. But as far as I understand, your implementation updates...
Hi, It is such a simple provided example. Could you please provide some more sophisticated examples such as how to bind modules with external third-party dynamic/static libraries (*.so/*.a)? Is there...
**Please describe the bug** Alpa-modified jaxlib can not be built on CPU-only environment. **Please describe the expected behavior** **System information and environment** - OS Platform and Distribution (e.g., Linux Ubuntu...
**System information** - Alpa version: - Are you willing to contribute it (Yes/No): Yes **Describe the new feature and the current behavior/state** Alpa currently can not support linux aarch64 because...
**Describe the bug** MLA reports `AssertionError: Keys and values must have the same shape!` when trying to reproduce DeepSeek2/3, which is caused by shape mismatching of key and vlaue input...
**Describe the bug** ValueError: multi_latent_attention does not support apply_rope_fusion. raise ValueError("multi_latent_attention does not support apply_rope_fusion.") **To Reproduce** ``` MLA_ARGS=( --multi-latent-attention --qk-pos-emb-head-dim 64 --qk-head-dim 128 --q-lora-rank 1536 --kv-lora-rank 512 --v-head-dim 128...
Hi, I installed decord on ubuntu 22.04 following the guide, but it failed running with popping up errors like ``` import decord File "/root/.local/lib/python3.10/site-packages/decord-0.6.0-py3.10-linux-aarch64.egg/decord/__init__.py", line 4, in from ._ffi.runtime_ctypes import...