enginex-ascend-910-llama.cpp/examples/model-conversion/requirements.txt

--extra-index-url https://download.pytorch.org/whl/cpu
torch
torchvision
transformers
huggingface-hub
accelerate
examples : install torch-cpu for model conversion tool/example (#15475) Signed-off-by: Jie Fu <jiefu@tencent.com> 2025-08-21 21:42:34 +08:00			`--extra-index-url https://download.pytorch.org/whl/cpu`
model-conversion : add extra debugging support for model conversion (#15877) * feat: Extra debugging support for model conversion - added BF16 support for llama-callback-eval and support for dumping intermediate steps in run-org-model.py 2025-09-09 06:05:55 +02:00			`torch`
			`torchvision`
			`transformers`
			`huggingface-hub`
			`accelerate`