[Bugfix][MoE] Restore TP-sharded routed-expert capture for DP=1 (#61388)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com> Signed-off-by: Ao Shen <281812371+aoshen02@users.noreply.github.com> Signed-off-by: Ao Shen <aoshen@inferact.ai> Co-authored-by: Ao Shen <281812371+aoshen02@users.noreply.github.com> Co-authored-by: OpenAI Codex <noreply@openai.com> Co-authored-by: Ao Shen <aoshen@inferact.ai>
This commit is contained in:
co-authored by
Ao Shen
OpenAI Codex
Ao Shen
parent
ef38e8d006
commit
a8be1500ba
@@ -327,10 +327,8 @@ def set_forward_context(
|
||||
vllm_config.parallel_config, num_tokens or 0, num_tokens_across_dp
|
||||
)
|
||||
|
||||
# Convenience: if cudagraph is used and num_tokens is given, we can just
|
||||
# create a batch descriptor here if not given (there's no harm since if it
|
||||
# doesn't match in the wrapper it'll fall through).
|
||||
if cudagraph_runtime_mode != CUDAGraphMode.NONE and num_tokens is not None:
|
||||
# Preserve the batch size before model-level sequence parallelism.
|
||||
if num_tokens is not None:
|
||||
batch_descriptor = batch_descriptor or BatchDescriptor(num_tokens=num_tokens)
|
||||
|
||||
additional_kwargs = current_platform.set_additional_forward_context(
|
||||
|
||||
Reference in New Issue
Block a user