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 11, 01:15 UTC
[Doc] Add vllm-metal to hardware plugin documentation (#31174)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Dec 22, 2025 at 15:06 UTC
95863540538804a48e31ca5806cefbac9d4c5326
2 files changed
+4
docs/getting_started/installation/README.md
+1
@@ -28,3 +28,4 @@ The backends below live **outside** the main `vllm` repository and follow the
28
| Cambricon MLU | `vllm-mlu` | <https://github.com/Cambricon/vllm-mlu> |
29
| Baidu Kunlun XPU | N/A, install from source | <https://github.com/baidu/vLLM-Kunlun> |
30
| Sophgo TPU | N/A, install from source | <https://github.com/sophgo/vllm-tpu> |
31
+| Apple Silicon (Metal) | N/A, install from source | <https://github.com/vllm-project/vllm-metal> |
docs/getting_started/installation/cpu.apple.inc.md
+3
@@ -4,6 +4,9 @@ vLLM has experimental support for macOS with Apple Silicon. For now, users must
4
5
Currently the CPU implementation for macOS supports FP32 and FP16 datatypes.
6
7
+!!! tip "GPU-Accelerated Inference with vLLM-Metal"
8
+ For GPU-accelerated inference on Apple Silicon using Metal, check out [vllm-metal](https://github.com/vllm-project/vllm-metal), a community-maintained hardware plugin that uses MLX as the compute backend.
9
+
10
# --8<-- [end:installation]
11
# --8<-- [start:requirements]
12