[Feat][RL] IPC weight sync optimizations: multigpu support and chunked packed tensors (#37476)

Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: hao-aaron <ahao@anyscale.com>
This commit is contained in:
Aaron Hao
2026-05-15 22:53:06 +08:00
committed by GitHub
parent 0fe7550254
commit e0a45f1455
10 changed files with 1591 additions and 455 deletions
+6 -1
View File
@@ -15,7 +15,12 @@ _TORCH_CUDA_PATTERNS = [
r"\bcuda_device_count_stateless\(\)\b",
]
ALLOWED_FILES = {"vllm/platforms/", "vllm/device_allocator/"}
ALLOWED_FILES = {
"vllm/platforms/",
"vllm/device_allocator/",
"vllm/distributed/weight_transfer/ipc_engine.py",
"tests/distributed/test_packed_tensor.py",
}
def scan_file(path: str) -> int: