Which GPUs does vLLM support?

vLLM 0.30.0: 40 of the 65 GPUs tracked here are supported, from the library's own requirements. Checked 2026-09-27.

The rule

Requirements as stated in vLLM's own installation docs at the v0.30.0 tag. The NVIDIA minimum has been compute capability 7.5 since at least v0.20.0 (checked at v0.20.0, 0.24.0, 0.26.0-0.29.0), so the V100 (7.0) is not supported. The AMD list is the docs' "GPU:" requirement line: MI200s (gfx90a), MI300 (gfx942), MI350 (gfx950), Radeon RX 7900 series (gfx1100/1101), Radeon RX 9000 series (gfx1200/1201), Ryzen AI MAX / AI 300 (gfx1151/1150).

Supported (40)

GPUVendorTargetDetails
B300 (Blackwell Ultra)NVIDIA10.3
DGX SparkNVIDIA12.1
RTX 5060 Ti 16GBNVIDIA12.0
RTX 5090NVIDIA12.0
RTX PRO 6000 BlackwellNVIDIA12.0
B200NVIDIA10.0
H200 SXM 141GBNVIDIA9.0
L40SNVIDIA8.9
RTX 4060 Ti 16GBNVIDIA8.9
H100 SXM5 80GBNVIDIA9.0
RTX 4090NVIDIA8.9
RTX 6000 Ada GenerationNVIDIA8.9
RTX 3060 12GBNVIDIA8.6
A100 SXM4 80GBNVIDIA8.0
RTX 3090NVIDIA8.6
T4NVIDIA7.5
TITAN RTXNVIDIA7.5
Instinct MI350XAMDgfx950
Instinct MI355XAMDgfx950
Radeon AI PRO R9700AMDgfx1201
Radeon RX 9060 XT (16GB)AMDgfx1200
Radeon RX 9060 XT (8GB)AMDgfx1200
Radeon RX 9070AMDgfx1201
Radeon RX 9070 XTAMDgfx1201
Ryzen AI Max+ 395AMDgfx1151
Instinct MI325XAMDgfx942
Instinct MI300AAMDgfx942
Instinct MI300XAMDgfx942
Radeon RX 7700 XTAMDgfx1101
Radeon RX 7800 XTAMDgfx1101
Radeon RX 7900 GREAMDgfx1100
Instinct MI210AMDgfx90a
Radeon RX 7900 XTAMDgfx1100
Radeon RX 7900 XTXAMDgfx1100
Instinct MI250XAMDgfx90a
Arc B580Intel—XPU backend: Intel Data Center GPU and Arc GPUs.
Data Center GPU Max 1550Intel—XPU backend: Intel Data Center GPU and Arc GPUs.
Arc A380Intel—XPU backend: Intel Data Center GPU and Arc GPUs.
Arc A750Intel—XPU backend: Intel Data Center GPU and Arc GPUs.
Arc A770 (16GB)Intel—XPU backend: Intel Data Center GPU and Arc GPUs.

Not supported (24)

GPUVendorTargetDetails
GTX 1080 TiNVIDIA6.1needs compute capability 7.5+
TITAN VNVIDIA7.0needs compute capability 7.5+
V100 SXM2 32GBNVIDIA7.0needs compute capability 7.5+
P100 SXM2 16GBNVIDIA6.0needs compute capability 7.5+
Tesla P40NVIDIA6.1needs compute capability 7.5+
TITAN X (Pascal)NVIDIA6.1needs compute capability 7.5+
M40 24GBNVIDIA5.2needs compute capability 7.5+
K80NVIDIA3.7needs compute capability 7.5+
Radeon RX 7600 XTAMDgfx1102
Radeon RX 6650 XTAMDgfx1032
Radeon RX 6750 XTAMDgfx1031
Radeon RX 6950 XTAMDgfx1030
Radeon RX 6600AMDgfx1032
Radeon RX 6700 XTAMDgfx1031
Instinct MI100AMDgfx908
Radeon RX 6800AMDgfx1030
Radeon RX 6800 XTAMDgfx1030
Radeon RX 6900 XTAMDgfx1030
Radeon VIIAMDgfx906
Radeon Instinct MI50AMDgfx906
Radeon Instinct MI60AMDgfx906
Radeon Instinct MI25AMDgfx900
Radeon Instinct MI6AMDgfx803
Radeon Instinct MI8AMDgfx803

Not enough data (1)

GPUVendorTargetDetails
Instinct MI455XAMD—gfx target not recorded

Sources: github.com/vllm-project/vllm/blob/v0.30.0/docs/getting_started/installation/gpu.cuda.inc.md, github.com/vllm-project/vllm/blob/v0.30.0/docs/getting_started/installation/gpu.rocm.inc.md, github.com/vllm-project/vllm/blob/v0.30.0/docs/getting_started/installation/gpu.xpu.inc.md

← All libraries, every GPU · Install checker