-
Notifications
You must be signed in to change notification settings - Fork 6k
Add Finegrained FP8 #11647
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Add Finegrained FP8 #11647
Conversation
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Just for bookkeeping, relaying stuff from our DM. I had to make the following changes to make this PR work: Expanddiff --git a/src/diffusers/models/modeling_utils.py b/src/diffusers/models/modeling_utils.py
index 638c5fbfb..737525143 100644
--- a/src/diffusers/models/modeling_utils.py
+++ b/src/diffusers/models/modeling_utils.py
@@ -1238,8 +1238,8 @@ class ModelMixin(torch.nn.Module, PushToHubMixin):
}
# Dispatch model with hooks on all devices if necessary
- print(model.transformer_blocks[0].attn.to_q.weight)
- print(model.transformer_blocks[0].attn.to_q.weight_scale_inv)
+ # print(model.transformer_blocks[0].attn.to_q.weight)
+ # print(model.transformer_blocks[0].attn.to_q.weight_scale_inv)
if device_map is not None:
device_map_kwargs = {
"device_map": device_map,
diff --git a/src/diffusers/quantizers/finegrained_fp8/finegrained_fp8_quantizer.py b/src/diffusers/quantizers/finegrained_fp8/finegrained_fp8_quantizer.py
index 5dec8b0b8..7212befcd 100644
--- a/src/diffusers/quantizers/finegrained_fp8/finegrained_fp8_quantizer.py
+++ b/src/diffusers/quantizers/finegrained_fp8/finegrained_fp8_quantizer.py
@@ -90,9 +90,9 @@ class FinegrainedFP8Quantizer(DiffusersQuantizer):
Quantizes weights to FP8 format using Block-wise quantization
"""
# print("############ create quantized param ########")
- from accelerate.utils import set_module_tensor_to_device
+ # from accelerate.utils import set_module_tensor_to_device
- set_module_tensor_to_device(model, param_name, target_device, param_value)
+ # set_module_tensor_to_device(model, param_name, target_device, param_value)
module, tensor_name = get_module_from_name(model, param_name)
@@ -131,8 +131,8 @@ class FinegrainedFP8Quantizer(DiffusersQuantizer):
scale = scale.reshape(scale_orig_shape).squeeze().reciprocal()
# Load into the model
- module._buffers[tensor_name] = quantized_param.to(target_device)
- module._buffers["weight_scale_inv"] = scale.to(target_device)
+ module._parameters[tensor_name] = quantized_param.to(target_device)
+ module._parameters["weight_scale_inv"] = scale.to(target_device)
# print("_buffers[0]", module._buffers["weight_scale_inv"])
def check_if_quantized_param(
Inference code: import torch
from diffusers import FluxPipeline, AutoModel, FinegrainedFP8Config
from diffusers.quantizers.finegrained_fp8.utils import FP8Linear
model_id = "black-forest-labs/FLUX.1-dev"
dtype = torch.bfloat16
quantization_config = FinegrainedFP8Config(
modules_to_not_convert=["norm", "proj_out", "x_embedder"], # weight_block_size=(32, 32)
)
transformer = AutoModel.from_pretrained(
model_id,
subfolder="transformer",
quantization_config=quantization_config,
torch_dtype=dtype,
device_map="cuda"
)
pipe = FluxPipeline.from_pretrained(
model_id,
transformer=transformer,
torch_dtype=dtype,
)
pipe.to("cuda")
for name, module in pipe.transformer.named_modules():
if isinstance(module, FP8Linear) and getattr(module, "weight_scale_inv", None) is not None:
if module.weight_scale_inv.ndim == 1:
print(name, module.weight_scale_inv.shape)
print(f"Pipeline memory usage: {torch.cuda.max_memory_reserved() / 1024**3:.3f} GB")
prompt = "A cat holding a sign that says hello world"
image = pipe(
prompt, num_inference_steps=50, guidance_scale=4.5, max_sequence_length=512
).images[0]
image.save("output.png")
print(f"Pipeline memory usage: {torch.cuda.max_memory_reserved() / 1024**3:.3f} GB") The |
What does this PR do?
Adds finegrained FP8