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

Jump to bottom

flashinfer: reminder to remove contiguous call in the future #2685

Merged
merged 1 commit into from
Oct 24, 2024
+2 −0
Merged

flashinfer: reminder to remove contiguous call in the future #2685

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
2 changes: 2 additions & 0 deletions server/text_generation_server/layers/attention/cuda.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@ def paged_attention(
from text_generation_server.layers.attention.flashinfer import decode_state

return decode_state.get().forward(
# TODO: remove `contiguous` call once https://github.com/flashinfer-ai/flashinfer/pull/553 is merged.
query.contiguous(),
paged_kv_cache=(kv_cache.key, kv_cache.value),
logits_soft_cap=softcap,
Expand Down Expand Up @@ -220,6 +221,7 @@ def attention(
softcap = 0.0

return prefill_with_paged_kv_state.get().forward(
# TODO: remove `contiguous` call once https://github.com/flashinfer-ai/flashinfer/pull/553 is merged.
query.contiguous(),
causal=causal,
paged_kv_cache=(kv_cache.key, kv_cache.value),
Expand Down
Loading