[AMD][Quantization] Add int4fp8_moe online quantization on ROCm (#7392)

Co-authored-by: Dehua Tang <dehtang@amd.com> Co-authored-by: HAI <hixiao@gmail.com> Co-authored-by: YC Tseng <yctseng@amd.com>
2026-01-14 01:44:40 -08:00
parent feae615b11
commit 5af84c8af5
12 changed files with 615 additions and 15 deletions
@@ -723,6 +723,7 @@ class ModelConfig:
            "quark",
            "mxfp4",
            "auto-round",
+            "quark_int4fp8_moe",
        ]
        optimized_quantization_methods = [
            "fp8",