(Phase 2)Add ModelOpt mixed FP8/NVFP4 support for image generation (#3570)

Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
This commit is contained in:
baonudesifeizhai authored and GitHub committed 2026-05-22 10:39:10 +08:00
1 parent 7d8816b46b
commit 076c34abfb
16 files changed
+768 -68

No files matched your search

+2 -2
View File
@@ -23,10 +23,10 @@ if TYPE_CHECKING:
)
# Pre-quantized checkpoints (modelopt FP8/FP4/MXFP8) only quantize the
# Pre-quantized checkpoints (modelopt FP8/FP4/MXFP8/mixed) only quantize the
# Thinker LM. Vision and audio encoder weights remain in BF16 with no
# corresponding scale tensors in the checkpoint.
PRE_QUANTIZED_METHODS: frozenset[str] = frozenset({"modelopt", "modelopt_fp4", "modelopt_mxfp8"})
PRE_QUANTIZED_METHODS: frozenset[str] = frozenset({"modelopt", "modelopt_fp4", "modelopt_mxfp8", "modelopt_mixed"})
def resolve_encoder_quant_config(