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 15, 16:00 UTC
doc: add info for macos clang errors (#16049)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
yihong committed
Apr 4, 2025 at 22:58 UTC
4ef0bb1fcfc6e948b8c9ac196ca5497bd2c9e157
1 file changed
+9
-1
docs/source/getting_started/installation/cpu/apple.inc.md
+9
-1
@@ -12,7 +12,7 @@ There are no pre-built wheels or images for this device, so you must build vLLM
12
13
- OS: `macOS Sonoma` or later
14
- SDK: `XCode 15.4` or later with Command Line Tools
15
-- Compiler: `Apple Clang >= 15.0.0`
15
+- Compiler: `Apple Clang >= 15.0.0` and `Apple Clang < 17.0.0`
16
17
## Set up using Python
18
@@ -51,6 +51,14 @@ If the build has error like the following snippet where standard C++ headers can
51
1 error generated.
52
```
53
54
+If run with error like the following snippet you need to check clang version and install a compatible version.
55
+
56
+```text
57
+AttributeError: '_OpNamespace' '_C' object has no attribute 'silu_and_mul'
58
+```
59
+
60
+More information can be found in <gh-issue:15941>.
61
+
62
## Set up using Docker
63
64
### Pre-built images