-
Im unable to make this work in comfyui, i put the .pth files in models/vae_approx but when running with the default taef1 in the load VAE node(unable to select it, but was there from the workflow used…
-
tested on both A800 and 4090 with script:
```
gpu=4
prompt="a photo of an astronaut riding a horse on mars"
args=(
--model /mnt/models/source/
--use_onediff
--pipefusion_parallel_degr…
-
```
(base) ➜ jupyter git:(master) ✗ ./train.sh
PyTorch version 2.0.0+cpu available.
generated new fontManager
/usr/local/lib/python3.8/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined…
-
### System Info
- `transformers` version: 4.43.3
- Platform: Linux-5.15.0-1074-azure-x86_64-with-glibc2.31
- Python version: 3.11.9
- Huggingface_hub version: 0.23.1
- Safetensors version: 0.4.…
-
branch off: origin/10391-dynamo-migrations-kysely-aurora-rds-tokens (till merged in)
DynamoDB Entities to Replace:
- docket-entry
- docket-entry-worksheet
- document
OpenSearch Indexes to Keep:
- ef…
-
branch off: origin/10391-dynamo-migrations-kysely-aurora-rds-tokens (till merged in)
DynamoDB Entities to Replace:
- case
OpenSearch Indexes to Keep:
- efcms-case (used to search cases)
convert the…
-
### 🐛 Describe the bug
Hi, we are trying to enabling Llama in Intel HPU, but found graph break in `torch.cuda.current_device()` . We have a package GPU migration tool, it replaces `torch.cuda.curre…
-
### 🐛 Describe the bug
When exporting a PyTorch model to ExecuTorch the following conversion script hangs on the line `edge_program = edge_program.to_backend(XnnpackPartitioner())`
`import torch
…
-
branch off: origin/10391-dynamo-migrations-kysely-aurora-rds-tokens (till merged in)
DynamoDB Entities to Replace:
- user-case-note
convert the functions in web-api/src/persistence/dynamo/userCase…
-
### Feature request
Compared to `symbolic_trace`, the new (but I assume, experimental) entrypoint in `torch._dynamo.export` seems to provide a more robust way to extract modular FX graphs, that can't…