@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / e4f0b4cd96
Fork 0

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): set cmake c++ compatible standard when building on MacOS CPU. (#23483)

Signed-off-by: teekenl <teekenlau@gmail.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

TeeKen Lau committed Sep 16, 2025 at 23:08 UTC e4f0b4cd96a9a729399759d9a54a861aacf57c18
1 file changed +18
docs/getting_started/installation/cpu/apple.inc.md
+18
@@ -52,6 +52,24 @@ uv pip install -e .
52 1 error generated.
53 ```
54
55 + ---
56 +
57 + If the build fails with C++11/C++17 compatibility errors like the following, the issue is that the build system is defaulting to an older C++ standard:
58 +
59 + ```text
60 + [...] error: 'constexpr' is not a type
61 + [...] error: expected ';' before 'constexpr'
62 + [...] error: 'constexpr' does not name a type
63 + ```
64 +
65 + **Solution**: Your compiler might be using an older C++ standard. Edit `cmake/cpu_extension.cmake` and add `set(CMAKE_CXX_STANDARD 17)` before `set(CMAKE_CXX_STANDARD_REQUIRED ON)`.
66 +
67 + To check your compiler's C++ standard support:
68 + ```bash
69 + clang++ -std=c++17 -pedantic -dM -E -x c++ /dev/null | grep __cplusplus
70 + ```
71 + On Apple Clang 16 you should see: `#define __cplusplus 201703L`
72 +
73 # --8<-- [end:build-wheel-from-source]
74 # --8<-- [start:pre-built-images]
75