[Quantization] Support online quantization with partially pre-quantized checkpoints (#51392)
Signed-off-by: Felix Marty <Felix.Marty@amd.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Codex <codex@openai.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
Codex
mgoin
parent
a11dfcff89
commit
5690b02c03
@@ -83,6 +83,7 @@ def test_fc_layer_quant_config_usage(default_vllm_config, dist_init, device) ->
|
||||
assert fc_no_quant.output_size == output_size
|
||||
|
||||
mock_quant_config = Mock()
|
||||
mock_quant_config.online_quantization_config = None
|
||||
fc_with_quant = ReplicatedLinear(
|
||||
input_size=input_size,
|
||||
output_size=output_size,
|
||||
|
||||
Reference in New Issue
Block a user