"vllm/executor/mp_distributed_executor.py" did not exist on "f666207161e5ecc2cd6ebab93c5a62cf44f30641"
Unverified Commit c802f543 authored by Gregory Shtrasberg's avatar Gregory Shtrasberg Committed by GitHub
Browse files

[ROCm][AMD][Build] Update AMD supported arch list (#15632)


Signed-off-by: default avatarGregory Shtrasberg <Gregory.Shtrasberg@amd.com>
parent cff8991a
...@@ -34,7 +34,7 @@ set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12") ...@@ -34,7 +34,7 @@ set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12")
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") 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")
# Supported AMD GPU architectures. # Supported AMD GPU architectures.
set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101") set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx950;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201")
# #
# Supported/expected torch versions for CUDA/ROCm. # Supported/expected torch versions for CUDA/ROCm.
......
...@@ -8,7 +8,7 @@ There are no pre-built wheels for this device, so you must either use the pre-bu ...@@ -8,7 +8,7 @@ There are no pre-built wheels for this device, so you must either use the pre-bu
## Requirements ## Requirements
- GPU: MI200s (gfx90a), MI300 (gfx942), Radeon RX 7900 series (gfx1100) - GPU: MI200s (gfx90a), MI300 (gfx942), Radeon RX 7900 series (gfx1100/1101), Radeon RX 9000 series (gfx1200/1201)
- ROCm 6.3 - ROCm 6.3
## Set up using Python ## Set up using Python
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment