Skip to content

Fix multimodal warmup #1465

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 2 commits into
base: habana_main
Choose a base branch
from
Open

Fix multimodal warmup #1465

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a93fa75
Fix mm wrmup
adobrzyn Jun 23, 2025
d861642
Unused var
adobrzyn Jun 23, 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
7 changes: 0 additions & 7 deletions vllm/worker/hpu_model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2761,7 +2761,6 @@ def warmup_graphs(self,

def _warmup_multimodal_graph(self,
kv_caches,
available_mem,
starting_mem=0,
total_batch_seq=0.001):

Expand All @@ -2775,11 +2774,6 @@ def _warmup_multimodal_graph(self,
_, max_seq_len = self.bucketing_ctx.get_max_prompt_shape()
seq_len = max_seq_len
batch_seq = 1 * num_patches
# Graph memory usage is proportional to seq dimension in a batch
mem_estimate = batch_seq / total_batch_seq * total_mem
if mem_estimate >= available_mem:
captured_all = False
continue
graphed_multimodal_bucket = num_patches
if graphed_multimodal_bucket in self.graphed_multimodal_buckets:
continue
Expand All @@ -2797,7 +2791,6 @@ def _warmup_multimodal_graph(self,

used_mem = align_workers(mem_prof.consumed_device_memory,
torch.distributed.ReduceOp.MAX)
available_mem -= used_mem
total_mem += used_mem
total_batch_seq += batch_seq

Expand Down