[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
@@ -100,6 +100,11 @@ def log_online_quantization(vllm_config: VllmConfig) -> None:
)
quant_config = vllm_config.quant_config
online_quantization_config = getattr(
quant_config, "online_quantization_config", None
)
if isinstance(online_quantization_config, OnlineQuantizationConfig):
quant_config = online_quantization_config
if not isinstance(quant_config, OnlineQuantizationConfig):
return