Skip to content

[Inference Benchmark] Copy llama4 model code from transformers #5388

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

[Inference Benchmark] Copy llama4 model code from transformers #5388

Show file tree
Hide file tree
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 benchmarks/python/benchmark_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,6 @@
ColwiseParallel,
)
from tqdm import tqdm
from transformers import AutoModelForCausalLM
from transformers.models.llama4 import Llama4TextConfig
from transformers.cache_utils import HybridChunkedCache
from transformers.models.llama4.modeling_llama4 import Llama4TextMoe
Expand All @@ -50,6 +49,7 @@
NVFP4InferenceLinear,
nvfuser_f16a_nvfp4weight_scaled_grouped_mm,
nvfuser_f16a_nvfp4weight_scaled_mm,
copied_Llama4ForCausalLM,
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nitpick, we could use a better name on this 😜

)
from thunder.torch.custom_op import _register_custom_op

Expand Down Expand Up @@ -279,7 +279,7 @@ def _load_model(self) -> torch.nn.Module:
self.hf_config = config

with DEVICE:
model = AutoModelForCausalLM.from_config(config, torch_dtype=torch.bfloat16)
model = copied_Llama4ForCausalLM._from_config(config)

return model

Expand Down
Loading
Loading