NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-26 06:38:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Sync v13.3-public from internal repo

Browse Source
This commit is contained in:
cuda-samples sync
2026-05-27 21:03:57 +00:00
parent aeab82ff30
commit 99686e0c71
150 changed files with 7977 additions and 246 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
python/4_DistributedComputing/ipcMemoryPool/README.md
View File

@@ -68,8 +68,8 @@ round-trip test:
- CUDA Toolkit 13.0 or newer (matches `cuda-python` 13.x)
- Python 3.10 or newer
- `cuda-python` (>=13.0.0)
- `cuda-core` (>=0.6.0)
- `cupy-cuda13x` (>=13.0.0)
- `cuda-core` (>=1.0.0)
- `cupy-cuda13x` (>=14.0.0)
## Installation
@@ -83,8 +83,8 @@ pip install -r requirements.txt
The `requirements.txt` installs:
- `cuda-python` (>=13.0.0)
- `cuda-core` (>=0.6.0)
- `cupy-cuda13x` (>=13.0.0)
- `cuda-core` (>=1.0.0)
- `cupy-cuda13x` (>=14.0.0)
## How to Run

2
python/4_DistributedComputing/ipcMemoryPool/ipcMemoryPool.py
View File

@@ -175,7 +175,7 @@ def main() -> int:
f"(is_ipc_enabled={mr.is_ipc_enabled})"
)
buffer = mr.allocate(nbytes)
buffer = mr.allocate(nbytes, stream=device.default_stream)
try:
# Fill the buffer with a known pattern from the parent side.
arr = cp.from_dlpack(buffer).view(dtype=cp.float32)

4
python/4_DistributedComputing/ipcMemoryPool/requirements.txt
View File

@@ -1,4 +1,4 @@
cuda-python>=13.0.0
cuda-core>=0.6.0
cupy-cuda13x>=13.0.0
cuda-core>=1.0.0
cupy-cuda13x>=14.0.0
numpy>=1.24.0