MCPcopy
hub / github.com/InternLM/lmdeploy / quantization_all

Function quantization_all

autotest/tools/quantization/test_quantization_awq.py:39–47  ·  view source on GitHub ↗
(config, quantization_model_name, origin_model_name, quantization_type, cuda_prefix: str = '')

Source from the content-addressed store, hash-verified

37
38
39def quantization_all(config, quantization_model_name, origin_model_name, quantization_type, cuda_prefix: str = ''):
40 result, msg = quantization(config, quantization_model_name, origin_model_name, quantization_type, cuda_prefix)
41 log_path = config.get('log_path')
42 quantization_log = os.path.join(
43 log_path, '_'.join(['quantization', quantization_type,
44 quantization_model_name.split('/')[1]]) + '.log')
45
46 allure.attach.file(quantization_log, name=quantization_log, attachment_type=allure.attachment_type.TEXT)
47 assert result, msg

Callers 3

test_quantization_awqFunction · 0.85
test_quantization_gptqFunction · 0.85
test_quantization_awq_prFunction · 0.85

Calls 3

quantizationFunction · 0.90
joinMethod · 0.80
getMethod · 0.45

Tested by

no test coverage detected