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

[TPU][Bugfix] Use XLA rank for persistent cache path #8137

Merged
merged 2 commits into from
Sep 4, 2024
Merged

[TPU][Bugfix] Use XLA rank for persistent cache path #8137

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
299a287
[TPU][Bugfix] Use XLA rank for persistent cache path
WoosukKwon Sep 4, 2024
7eeee26
Minor
WoosukKwon Sep 4, 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
2 changes: 1 addition & 1 deletion docs/source/getting_started/tpu-installation.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ First, install the dependencies:
$ export DATE="20240828"
$ export TORCH_VERSION="2.5.0"
$ pip install https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch-${TORCH_VERSION}.dev${DATE}-cp310-cp310-linux_x86_64.whl
$ pip3 install https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-${TORCH_VERSION}.dev${DATE}-cp310-cp310-linux_x86_64.whl
$ pip install https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-${TORCH_VERSION}.dev${DATE}-cp310-cp310-linux_x86_64.whl
$ # Install JAX and Pallas.
$ pip install torch_xla[tpu] -f https://storage.googleapis.com/libtpu-releases/index.html
Expand Down
3 changes: 2 additions & 1 deletion vllm/worker/tpu_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,8 +102,9 @@ def init_device(self) -> None:
# NOTE(woosuk): Set per-rank cache path since different ranks
# can have slightly different XLA graphs.
world_size = self.parallel_config.world_size
rank = xr.global_ordinal()
per_rank_path = os.path.join(envs.VLLM_XLA_CACHE_PATH,
f"tp{world_size}_rank{self.rank}")
f"tp{world_size}_rank{rank}")
xr.initialize_cache(per_rank_path, readonly=False)

def load_model(self):
Expand Down
Loading