Skip to content

[XPU]Fix out-of-memory issue during single-XPU deployment #3131

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

Merged
merged 2 commits into from
Aug 4, 2025
Merged

[XPU]Fix out-of-memory issue during single-XPU deployment #3131

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b00005a
Fix out-of-memory issue during single-XPU deployment
iosmers Aug 1, 2025
8568f1c
Merge branch 'release/2.1' into release/2.1
iosmers Aug 4, 2025
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
13 changes: 9 additions & 4 deletions fastdeploy/worker/xpu_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,9 +94,14 @@ def determine_available_memory(self) -> int:
xpu_get_used_global_memory,
)

total_memory = xpu_get_total_global_memory(self.local_rank)
used_memory = xpu_get_used_global_memory(self.local_rank)
free_memory = xpu_get_free_global_memory(self.local_rank)
assert self.device_ids[self.local_rank] is not None, f"device_id is none for rank {self.local_rank}"
assert (
len(self.device_ids) > self.local_rank
), f"device number must be greater than local rank, but get device number is {len(self.device_ids)}, rank is {self.local_rank}"

total_memory = xpu_get_total_global_memory(int(self.device_ids[self.local_rank]))
used_memory = xpu_get_used_global_memory(int(self.device_ids[self.local_rank]))
free_memory = xpu_get_free_global_memory(int(self.device_ids[self.local_rank]))

logger.info(
f"Before warm up, total_memory: {total_memory}, \
Expand All @@ -107,7 +112,7 @@ def determine_available_memory(self) -> int:
self.model_runner.profile_run()

total_available_memory = int(total_memory * self.cache_config.gpu_memory_utilization)
used_memory = xpu_get_used_global_memory(self.local_rank)
used_memory = xpu_get_used_global_memory(int(self.device_ids[self.local_rank]))
available_kv_cache_memory = total_available_memory - used_memory
model_block_memory_used = self.cal_theortical_kvcache()
available_kv_cache_memory += model_block_memory_used * self.parallel_config.total_block_num
Expand Down
Loading