Skip to content

Account for memory usage of other processes #18858

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

Closed
wants to merge 4 commits into from
Closed

Account for memory usage of other processes #18858

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
852c186
Account for memory usage of other processes
maxdebayser May 28, 2025
6e667bb
Merge branch 'upstream_main' into fix_memory_accounting
maxdebayser Jun 3, 2025
01d39bf
Merge branch 'upstream_main' into fix_memory_accounting
maxdebayser Jun 3, 2025
29d71a1
Merge branch 'upstream_main' into fix_memory_accounting
maxdebayser Jun 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
4 changes: 3 additions & 1 deletion vllm/v1/worker/gpu_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,7 +205,9 @@ def determine_available_memory(self) -> int:
)["allocated_bytes.all.current"]
total_allocated_bytes = torch.cuda.mem_get_info(
)[1] - torch.cuda.mem_get_info()[0]
non_torch_allocations = total_allocated_bytes - torch_allocated_bytes
init_allocated = total_gpu_memory - self.init_gpu_memory
non_torch_allocations = total_allocated_bytes - torch_allocated_bytes \
- init_allocated
if non_torch_allocations > 0:
peak_memory += non_torch_allocations
available_kv_cache_memory = (
Expand Down