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 15, 17:15 UTC
[ROCm][AMD][Build] Update AMD supported arch list (#15632)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Gregory Shtrasberg committed
Mar 28, 2025 at 23:39 UTC
c802f5430d4a404744ed64adfddda18dd57e525a
2 files changed
+2
-2
CMakeLists.txt
+1
-1
@@ -34,7 +34,7 @@ set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12")
34
set(CUDA_SUPPORTED_ARCHS "7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0;10.0;10.1;12.0")
35
36
# Supported AMD GPU architectures.
37
-set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101")
37
+set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx950;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201")
38
39
#
40
# Supported/expected torch versions for CUDA/ROCm.
docs/source/getting_started/installation/gpu/rocm.inc.md
+1
-1
@@ -8,7 +8,7 @@ There are no pre-built wheels for this device, so you must either use the pre-bu
8
9
## Requirements
10
11
-- GPU: MI200s (gfx90a), MI300 (gfx942), Radeon RX 7900 series (gfx1100)
11
+- GPU: MI200s (gfx90a), MI300 (gfx942), Radeon RX 7900 series (gfx1100/1101), Radeon RX 9000 series (gfx1200/1201)
12
- ROCm 6.3
13
14
## Set up using Python