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

Remove restriction on using compile + sharding #707

Merged
merged 1 commit into from
Dec 9, 2024
Merged

Remove restriction on using compile + sharding #707

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 0 additions & 3 deletions server/lorax_server/models/flash_causal_lm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1319,9 +1319,6 @@ def warmup(self, batch: FlashCausalLMBatch, max_new_tokens: int, embedding_model

graph_cache_memory = 0
if self.compile:
if self.world_size > 1:
raise ValueError("Cannot enable `--compile` when sharding across multiple GPUs")

# Estimate the memory overhead from CUDA graphs so we can subtract it from the kv cache.
# Needs to be estimated here rather than fully initialized as the graph cache relies on the
# cache manager being set.
Expand Down
Loading