Skip to content

open fla support for XPU to benefit from the acceleration - #47799

Open
kaixuanliu wants to merge 1 commit into
huggingface:mainfrom
kaixuanliu:fla-xpu
Open

open fla support for XPU to benefit from the acceleration#47799
kaixuanliu wants to merge 1 commit into
huggingface:mainfrom
kaixuanliu:fla-xpu

Conversation

@kaixuanliu

@kaixuanliu kaixuanliu commented Aug 5, 2026

Copy link
Copy Markdown
Contributor

CI

@IlyasMoutawwakil pls help review, thx! I used Qwen3.5 to do a benchmark, results showed we can get significant speedup especially during prefill stage.Here is an example for chunk_gated_delta_rule op:

seq_len torch fla Speedup
128 6.86 ms 0.90 ms 7.6 x
512 8.82ms 1.26 ms 7.1 x
2048 17.00 ms 3.03 ms 5.6 x

Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>
@github-actions

github-actions Bot commented Aug 5, 2026

Copy link
Copy Markdown
Contributor

CI recap

Dashboard: View test results in Grafana
Latest run: 31012052835
Result: success | Grafana metrics are not available yet.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant