Skip to content
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

Device Type HPU support for torch.generator() API #628

Open
wants to merge 4 commits into
base: habana_main
Choose a base branch
from
Open

Device Type HPU support for torch.generator() API #628

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ab085c8
added HPU specific changes
Nov 8, 2024
9e69339
Added support for HPU device type
Dec 13, 2024
b464af9
removed additional benchmarks not required
Dec 13, 2024
84d6620
Merge branch 'habana_main' into habana_main
nageshdn Dec 17, 2024
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
12 changes: 10 additions & 2 deletions vllm/model_executor/model_loader/weight_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -615,9 +615,17 @@ def initialize_dummy_weights(
# XLA device does not support torch.Generator()
param.uniform_(low, high)
continue
if current_platform.is_hpu():
import habana_frameworks.torch.hpu.random as htrandom
generator = \
htrandom.default_generators[
0].manual_seed(seed)
else:
generator = torch.Generator(device=device).manual_seed(
seed)
#generator = torch.Generator(device=param.data.device)
#generator.manual_seed(seed)

generator = torch.Generator(device=param.data.device)
generator.manual_seed(seed)
if torch.finfo(param.data.dtype).bits < 16:
# uniform_ doesn't support < 16-bit datatypes (FP8)
dtype = param.data.dtype
Expand Down