-
We need to figure out how to get the smiles into RDKit to build the graph for the gnn.
-
### 🐛 Describe the bug
The variable order in ```nearest``` is flipped.
The documentation stated "Finds for each element in `y` the `k` nearest point in `x`", which means the output dimension shou…
-
我的命令：
```shell
vllm serve TeleChat2-7B \
--trust-remote-code \
--max-model-len 2000 \
--tensor-parallel-size 2 \
--dtype float16 --port 10000
```
运行之后，会一直卡在一步，不继续加载模型：
```shell
INFO 11-2…
-
Upon building autodoc, I encountered the following import error:
```
$ cd doc
$ make html
Running Sphinx v8.1.3
loading translations [en]... done
making output direc…
-
-
Because the [problem described](https://github.com/tenstorrent/pytorch2.0_ttnn/pull/383) in there, so there always followed by an `aten.to_copy.default`
And because there will [at least remain an ate…
-
### What happened?
For the given IR
```mlir
module {
func.func @torch_jit(%arg1: !torch.vtensor, %arg2: !torch.vtensor) -> !torch.vtensor attributes {torch.onnx_meta.ir_version = 7 : si64, torch.…
-
### System Info
```
- `transformers` version: 4.46.3
- Platform: Linux-6.8.0-1015-aws-x86_64-with-glibc2.35
- Python version: 3.12.6
- Huggingface_hub version: 0.26.2
- Safetensors version: 0.…
-
### What happened?
The flux-dev text encoder (CLIP + t5XXL) fails to lower in all precisions (fp32, bf16, fp16) with the following error:
```
iree-compile --iree-hal-target-device=amdgpu --iree-hip-t…
-
Dear @dfalbel as you probably already known, `torch` is crashing in R-4.4.2 for MacOS. The problem is caused because R-4.4 for MacOS now includes an OpenMP library as a common run-time support for the…