Skip to content

MTP Linear support fp8 gemm #10244

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.

Sign up for GitHub

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

Open
zhangbo9674 wants to merge 1 commit into
base: dsv3_dev
Choose a base branch
from
Open

MTP Linear support fp8 gemm #10244

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions paddlenlp/transformers/deepseek_v2/modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@
from ..utils import device_guard
from . import fp8_linear as linear_utils
from .configuration import DeepseekV2Config
from .fp8_linear import FP8DeepseekV2MLP, FP8Linear, Linear, FP8KeepXLinear
from .fp8_linear import FP8DeepseekV2MLP, FP8KeepXLinear, FP8Linear, Linear

DSV3_USE_FP8_GEMM = os.getenv("DSV3_USE_FP8_GEMM", "False").lower() == "true"
Linear = FP8Linear if DSV3_USE_FP8_GEMM else Linear
Expand Down Expand Up @@ -1393,7 +1393,7 @@ def __init__(

self.enorm = DeepseekV2RMSNorm(config)
self.hnorm = DeepseekV2RMSNorm(config)
self.eh_proj = nn.Linear(2 * config.hidden_size, config.hidden_size)
self.eh_proj = Linear(2 * config.hidden_size, config.hidden_size)

def forward(
self,
Expand Down
Loading