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 14, 05:30 UTC
[Doc] Add Cambricon MLU support (#25942)
Signed-off-by: a120092009 <zhaoty0121@gmail.com>
a120092009 committed
Sep 30, 2025 at 17:59 UTC
8d0afa9b422d77c780ccc642c4fe8177aed7330c
1 file changed
+1
docs/getting_started/installation/README.md
+1
@@ -25,3 +25,4 @@ The backends below live **outside** the main `vllm` repository and follow the
25
| MetaX MACA GPU | N/A, install from source | <https://github.com/MetaX-MACA/vLLM-metax> |
26
| Rebellions ATOM / REBEL NPU | `vllm-rbln` | <https://github.com/rebellions-sw/vllm-rbln> |
27
| IBM Spyre AIU | `vllm-spyre` | <https://github.com/vllm-project/vllm-spyre> |
28
+| Cambricon MLU | `vllm-mlu` | <https://github.com/Cambricon/vllm-mlu> |