[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:
Bolin Sun
2026-10-09 16:13:24 -07:00
committed by GitHub
co-authored by Claude Nick Hill
parent fa94ad4143
commit 04b02fc8a5
8 changed files with 1290 additions and 8 deletions
+1
View File
@@ -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