-
### Describe the issue
Issue:
Command:
```
PASTE THE COMMANDS HERE.
```
Log:
```
PASTE THE LOGS HERE.
```
from llava.model.builder import load_pretrained_model
from llava.mm_utils impo…
-
Build fails:
```
/usr/local/libexec/ccache/c++ -DH5_BUILT_AS_DYNAMIC_LIB -Dserac_numerics_EXPORTS -I/usr/ports/science/serac/work/serac-33946be/src/serac/infrastructure/../.. -I/usr/ports/science/se…
-
Qwen2-VL-72B-Instruct-GPTQ-Int4官方demo单图推理,transformers最新版本4.46.0.dev0,权重加载出现如下:
Some weights of Qwen2VLForConditionalGeneration were not initialized from the model checkpoint at /home/nas01/grp_FACE/…
-
你好,我在运行训练代码,model.py文件里面这一段:
input_c2ws=torch.tensor(batch['input_c2ws'])
print(input_c2ws.shape)
#nput_c2ws=np.array(batch['input_c2ws'].cpu())
input_c2ws=input_c2ws.resha…
-
I am encountering an `AttributeError` when trying to deploy the `nveagle-eagle-x5-13b-chat` model using Docker. The error occurs deep within the `accelerate` library's hook management, specifically wh…
hl2dm updated
3 weeks ago
-
### Use Case
Most solid material models require tensor operations to compute stress $\mathbf{S}$ and tangent matrix $\mathrm{C}$. The tensors are usually 2nd- and 4th-order fixed-size, `nsd x nsd` an…
-
Currently, in lmcache_vllm, we do memory copy and `tensor.contiguous`
Should profile the overhead and estimate what could be the gain.
-
Right now what we have is docstrings but they could use work - this came up as @vayuda was looking at extending his bitpacking work to include a notion of scales
1. What does tensor core layout mea…
-
### 🚀 The feature, motivation and pitch
Non-leaf tensors can be set to retain gradients with `tensor.retain_grad()`, after which `tensor.retains_grad is True` (for non-leaf tensors only it seems).
…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussi…