[Bugfix] LoRA for DeepSeek V3.2 (#35077)
Signed-off-by: Hollow Man <hollowman@opensuse.org> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
co-authored by
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Jee Jee Li
parent
04eac6ba24
commit
a250f1bd5f
@@ -1620,18 +1620,13 @@ def _parallel_worker(
|
||||
else:
|
||||
print("F", end="")
|
||||
finally:
|
||||
# Note: for some reason DeepEP buffers don't seem to be
|
||||
# entirely reusable on B200. In order to work around this
|
||||
# we clear the all2all manager's cache after each testpoint.
|
||||
cap = current_platform.get_device_capability()
|
||||
if (
|
||||
cap is not None
|
||||
and cap.major == 10
|
||||
and (
|
||||
test_config.backend == "deepep_low_latency"
|
||||
or test_config.backend == "deepep_high_throughput"
|
||||
)
|
||||
):
|
||||
# DeepEP managers are not reliably reusable across many subtests in
|
||||
# a single worker process. Tear them down after each DeepEP case so
|
||||
# later subtests do not inherit stale communication state.
|
||||
if test_config.backend in {
|
||||
"deepep_low_latency",
|
||||
"deepep_high_throughput",
|
||||
}:
|
||||
torch.accelerator.synchronize()
|
||||
all2all_manager = get_ep_group().device_communicator.all2all_manager
|
||||
if all2all_manager is not None:
|
||||
|
||||
Reference in New Issue
Block a user