[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:
fxmarty-amd
2026-09-04 11:46:06 -07:00
committed by GitHub
co-authored by Codex mgoin
parent a11dfcff89
commit 5690b02c03
25 changed files with 846 additions and 175 deletions
@@ -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,