e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
62 lines
1.8 KiB
Python
62 lines
1.8 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
# can only run on machines with p2p access across GPUs
|
|
# can only run with torchrun:
|
|
# torchrun --nproc_per_node=2 tests/distributed/test_ca_buffer_sharing.py
|
|
|
|
import ctypes
|
|
|
|
import torch
|
|
import torch.distributed as dist
|
|
|
|
from vllm.distributed.device_communicators.cuda_wrapper import CudaRTLibrary
|
|
from vllm.distributed.device_communicators.custom_all_reduce import ( # noqa
|
|
CustomAllreduce)
|
|
|
|
# create a cpu process group for communicating metadata (ipc handle)
|
|
dist.init_process_group(backend="gloo")
|
|
rank = local_rank = dist.get_rank()
|
|
world_size = dist.get_world_size()
|
|
|
|
# every process sets its own device (differently)
|
|
lib = CudaRTLibrary()
|
|
lib.cudaSetDevice(rank)
|
|
|
|
buffer_size_in_bytes = 1024
|
|
byte_value = 2 # the value we write to the buffer for verification
|
|
|
|
pointers = CustomAllreduce.create_shared_buffer(buffer_size_in_bytes)
|
|
|
|
print(f"Rank {rank} has pointers {pointers}")
|
|
|
|
dist.barrier()
|
|
torch.cuda.synchronize()
|
|
|
|
if rank == 0:
|
|
# the first rank tries to write to all buffers
|
|
for p in pointers:
|
|
pointer = ctypes.c_void_p(p)
|
|
lib.cudaMemset(pointer, byte_value, buffer_size_in_bytes)
|
|
|
|
dist.barrier()
|
|
torch.cuda.synchronize()
|
|
|
|
host_data = (ctypes.c_char * buffer_size_in_bytes)()
|
|
|
|
# all ranks read from all buffers, and check if the data is correct
|
|
for p in pointers:
|
|
pointer = ctypes.c_void_p(p)
|
|
lib.cudaMemcpy(host_data, pointer, buffer_size_in_bytes)
|
|
for i in range(buffer_size_in_bytes):
|
|
assert ord(host_data[i]) == byte_value, (
|
|
f"Rank {rank} failed"
|
|
f" to verify buffer {p}. Expected {byte_value}, "
|
|
f"got {ord(host_data[i])}")
|
|
|
|
print(f"Rank {rank} verified all buffers")
|
|
|
|
dist.barrier()
|
|
torch.cuda.synchronize()
|
|
|
|
CustomAllreduce.free_shared_buffer(pointers)
|