Files
xc-llm-ascend/tests
sdmyzlp 53c2d58ae1 Handle with_prefill_across_dp for multistream mla (#1322)
### What this PR does / why we need it?
After #1094, decode might be executed with non-compiled mode, despite of
`torchair_graph_config.enabled`, causing multistream mla to fail, which
assumes torchair compiled mode for decode when
`torchair_graph_config.enabled == True`.
Augment that assumption to fix this.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
Tested both offline, and by graph mode mla e2e testcase.

---------

Signed-off-by: sdmyzlp <lrwei2@petalmail.com>
2025-06-26 09:32:07 +08:00
..
2025-05-28 06:31:35 +08:00