Functions — github.com/OpenGVLab/EfficientQAT

CodeHub MCPcopy Create free account

hub / github.com/OpenGVLab/EfficientQAT / functions

Functions110 in github.com/OpenGVLab/EfficientQAT

⨍ Functions 110◇ Types & classes 25

quantize/triton_utils/kernels.py:215

Methodstate_dict

Methodto_gradio_chatbot

Convert the conversation to gradio chatbot format.

deita_dataset/conversation.py:209

Methodto_openai_api_messages

Convert the conversation to OpenAI chat completion format.

deita_dataset/conversation.py:219

Functiontokenize_function

datautils_e2e.py:166

Functiontruncate_number

(number, threshold=1e-2)

quantize/utils.py:95

Methodupdate_last_message

Update the last output. The last message is typically set to be None when constructing the prompt, so we need to update it in-place a

deita_dataset/conversation.py:201

(cls, model, transpose=False, seqlen=2048)

quantize/int_linear_real.py:22

(self, *args, **kwargs)

quantize/triton_utils/custom_autotune.py:122

(cls, model, transpose=False, seqlen=2048)

quantize/triton_utils/mixin.py:3

← previous101–110 of 110, ranked by callers