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 13, 14:30 UTC
[ROCm][Platform] Add RX7900XTX device id in _ROCM_DEVICE_ID_NAME_MAP (#28279)
Signed-off-by: JartX <sagformas@epdcenter.es>
JartX committed
Nov 10, 2025 at 00:09 UTC
c5f685b3ae5fef9dec499f401427b33075673da8
1 file changed
+1
vllm/platforms/rocm.py
+1
@@ -77,6 +77,7 @@ _ROCM_DEVICE_ID_NAME_MAP: dict[str, str] = {
77
"0x74b9": "AMD_Instinct_MI325X", # MI325X VF
78
"0x74a9": "AMD_Instinct_MI300X_HF",
79
"0x74bd": "AMD_Instinct_MI300X_HF",
80
+ "0x744c": "AMD_Radeon_RX7900XTX",
81
}
82
83
# Prevent use of clashing `{CUDA/HIP}_VISIBLE_DEVICES`