[Rebase] Rebase to vllm 0.28.0 (#6606)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
da4a08b65b
commit
651b03225b
42 files changed
+931
-121
No files matched your search
@@ -1,5 +1,5 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
|
||||
"""INT8 quantization config for diffusion transformers.
|
||||
|
||||
Supports both online (dynamic) and offline (checkpoint) INT8 quantization
|
||||
@@ -26,10 +26,12 @@ from vllm.model_executor.layers.quantization.base_config import (
|
||||
QuantizationConfig,
|
||||
QuantizeMethodBase,
|
||||
)
|
||||
from vllm.model_executor.layers.quantization.fp8 import CopyNumelCounter
|
||||
from vllm.model_executor.layers.quantization.utils.quant_utils import (
|
||||
is_layer_skipped,
|
||||
)
|
||||
from vllm.model_executor.model_loader.reload.meta import (
|
||||
CopyCounter as CopyNumelCounter,
|
||||
)
|
||||
from vllm.model_executor.model_loader.weight_utils import initialize_single_dummy_weight
|
||||
from vllm.model_executor.parameter import (
|
||||
ChannelQuantScaleParameter,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
|
||||
"""W8A8 MXFP8 (Microscaling FP8) online/offline quantization for diffusion transformers.
|
||||
|
||||
Architecture:
|
||||
@@ -49,8 +49,10 @@ from vllm.model_executor.layers.quantization.base_config import (
|
||||
QuantizationConfig,
|
||||
QuantizeMethodBase,
|
||||
)
|
||||
from vllm.model_executor.layers.quantization.fp8 import CopyNumelCounter
|
||||
from vllm.model_executor.layers.quantization.utils.quant_utils import is_layer_skipped
|
||||
from vllm.model_executor.model_loader.reload.meta import (
|
||||
CopyCounter as CopyNumelCounter,
|
||||
)
|
||||
from vllm.model_executor.model_loader.weight_utils import initialize_single_dummy_weight
|
||||
from vllm.model_executor.parameter import ModelWeightParameter
|
||||
from vllm.model_executor.utils import replace_parameter
|
||||
|
||||
@@ -157,7 +157,10 @@ class DiffusionSVDQuantConfig(QuantizationConfig):
|
||||
prefix,
|
||||
self.modules_to_not_convert,
|
||||
self.packed_modules_mapping,
|
||||
skip_with_substr=True,
|
||||
# vLLM 0.28: skip_with_substr was replaced by match_mode
|
||||
# ("substring" preserves the v0.27 skip_with_substr=True
|
||||
# behavior verbatim).
|
||||
match_mode="substring",
|
||||
):
|
||||
return UnquantizedLinearMethod()
|
||||
return DiffusionSVDQuantLinearMethod(self)
|
||||
|
||||
Reference in new issue
Block a user