[Core] shm tensor arena for efficient cpu->gpu worker broadcast (#51207)
Signed-off-by: Bolin Sun <bolins@nvidia.com> Signed-off-by: <bolins@nvidia.com> Signed-off-by: Nick Hill <nickhill123@gmail.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
co-authored by
Claude
Nick Hill
parent
fa94ad4143
commit
04b02fc8a5
@@ -166,6 +166,7 @@ class MultiprocExecutor(Executor):
|
||||
self.local_world_size,
|
||||
max_chunk_bytes=max_chunk_bytes,
|
||||
connect_ip=mq_connect_ip,
|
||||
enable_shm_tensor_arena=(self.parallel_config.enable_shm_tensor_arena),
|
||||
)
|
||||
scheduler_output_handle = self.rpc_broadcast_mq.export_handle()
|
||||
# Create workers
|
||||
|
||||
Reference in New Issue
Block a user