rm triton from requirements.txt (#824)

Author: wenhuach21

README.md

@@ -5,7 +5,7 @@ AutoRound
 ===========================
 <h3> Advanced Quantization Algorithm for LLMs</h3>
 
-[![python](https://img.shields.io/badge/python-3.9%2B-blue)](https://github.com/intel/auto-round)
+[![python](https://img.shields.io/badge/python-3.10%2B-blue)](https://github.com/intel/auto-round)
 [![version](https://img.shields.io/badge/release-0.7.0-green)](https://github.com/intel/auto-round)
 [![license](https://img.shields.io/badge/license-Apache%202-9C27B0)](https://github.com/intel/auto-round/blob/main/LICENSE)
 <a href="https://huggingface.co/Intel">

auto_round/utils.py

@@ -17,7 +17,6 @@
 import gc
 import importlib
 import json
-import logging
 import os
 import re
 import sys
@@ -66,7 +65,7 @@ def __contains__(self, key):
         return True if key in self._support_list else False
 
     def __str__(self):
-        ##return "(%s)" % ', '.join(self._support_format + ("gguf:q*_0", "gguf:q*_1", "gguf:q*_k_s"))
+        # Return "(%s)" % ', '.join(self._support_format + ("gguf:q*_0", "gguf:q*_1", "gguf:q*_k_s"))
         return "(%s)" % ", ".join(self._support_list)
 
     def __getitem__(self, key):
@@ -77,7 +76,7 @@ def __getitem__(self, key):
 SUPPORTED_FORMATS = SupportedFormats()
 SUPPORTED_LAYER_TYPES = (torch.nn.Linear, transformers.pytorch_utils.Conv1D)
 
-##changed to str as it relies triton or others lib to load this
+# Changed to str as it relies on triton or others lib to load this
 INNER_SUPPORTED_LAYER_TYPES = ("FP8Linear",)
 # INNER_SUPPORTED_LAYER_TYPES = (transformers.integrations.finegrained_fp8.FP8Linear,)
 

requirements.txt

@@ -8,7 +8,6 @@ packaging
 pillow
 numba
 tbb
-triton ## for fp8 model
 torch
 transformers>=4.38
 threadpoolctl