A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 7, 16:30 UTC
[ROCm] Update the torch version in rocm_build.txt to use the official 2.10 release (#34387)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Sage Moore committed
Feb 26, 2026 at 08:28 UTC
9e2cabdf9c86e9fceca8842c8ea2a260281c31e8
1 file changed
+2
-2
requirements/rocm-build.txt
+2
-2
@@ -1,7 +1,7 @@
1
# Common dependencies
2
-r common.txt
3
4
---extra-index-url https://download.pytorch.org/whl/test/rocm7.0
4
+--extra-index-url https://download.pytorch.org/whl/rocm7.1
5
torch==2.10.0
6
torchvision==0.25.0
7
torchaudio==2.10.0
@@ -12,5 +12,5 @@ setuptools>=77.0.3,<80.0.0
12
setuptools-scm>=8
13
wheel
14
jinja2>=3.1.6
15
-amdsmi==6.4.3
15
+amdsmi==7.0.2
16
timm>=1.0.17