[Model][Hardware][AMD][Kernel] Part 2/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_ATTN (#42755)
Signed-off-by: Jack Hu <Jack.Hu@amd.com> Signed-off-by: Jack Hu <jingxujaster@hotmail.com> Signed-off-by: Jack Hu <jack.hu@amd.com> Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
This commit is contained in:
@@ -368,9 +368,11 @@ async def test_dp_pause_late_request_does_not_block_drain():
|
||||
# down first. The front-end sets its own copy optimistically when it
|
||||
# forwards the wake, so sample only after several coordinator
|
||||
# publishes (every 100ms while stats change) have overwritten it.
|
||||
# Rank 0 reports the wave only after its first step, which can outlast
|
||||
# the 2s on a cold device, so wait for the report rather than sample it.
|
||||
await asyncio.sleep(2)
|
||||
assert not long_request.done(), "the warmup request was too short to sample"
|
||||
assert engine.engine_core.dp_engines_running(), (
|
||||
assert await _poll_flag(engine, True, timeout=30), (
|
||||
"the coordinator does not report the engines as running while they are"
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user