-
### Expected behavior
```python
with qml.tape.QuantumTape() as temp_go:
qml.CNOT([1, 2])
qml.CNOT([0, 1])
qml.CNOT([2, 3])
qml.CNOT([1, 2])
qml.CNOT([2, 3])
qm…
-
The current implementation of `scatter` has some limitation.
1. the GPU implementation hard coded iterator bindings which might not work for certain devices. For example, for OpenCL backend, if a GP…
-
I learned from the Adreno GPU optimization manual(https://developer.qualcomm.com/download/adrenosdk/adreno-opencl-programming-guide.pdf?referrer=node/6114):
Avoid using the function called async_wo…
-
I used `nn.GPU` to allocate model on different GPUs. Things were going well until I flattened the parameters and gradParameters for optimization.
Here is my code:
```
local model = nn.Sequenti…
-
我尝试转化7B的量化模型都失败了，AWQ提示仅支持GPU，GPTQ则提示.float()不支持量化模型，请问你转化过量化模型吗，或者说是否无法转化量化模型？我看test中有一个loss.float(), 但是感觉也无从下手。谢谢！
-
### Describe the issue
I have a model that is 4137 MB as a .onnx, exported from a PyTorch's `ScriptModule` through `torch.onnx.export`.
When loading the ONNX model through an InferenceSession us…
-
Below are typical usages to change the optimization level of some Fortran files:
```
set(NOOPT
eam/src/physics/cam/zm_conv.F90)
if (NOT DEBUG)
foreach(ITEM IN LISTS NOOPT)
e3sm_deoptim…
dqwu updated
3 months ago
-
### Milestones:
- Study 3DGS implementations and identify best option, risks and blockers for integration
- Study [filament renderer](https://google.github.io/filament/Filament.html) and Open3D-fi…
-
If run this code:
```python
model = Qwen2VLForConditionalGeneration.from_pretrained(
"Qwen/Qwen2-VL-7B-Instruct",
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
…
-
### 🚀 The feature, motivation and pitch
# Motivation
For complicated `DTensor` redistribution (e.g. `[S(0), S(1)] -> [S(1), S(0)]`), it's likely that only GPU1 and GPU2 need to communicate (when t…
botbw updated
2 months ago