happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: apply clang-format to CUDA macros (#16017) 

clang-format previously broke long CUDA macros (e.g. __launch_bounds__) into
unreadable line breaks inside template declarations, such as:

  template<int D, int ncols, int nwarps, int VKQ_stride,
           typename KQ_acc_t, bool use_logit_softcap>
      __launch_bounds__(nwarps*ggml_cuda_get_physical_warp_size(), 1)

This change adjusts formatting rules so that CUDA macros remain consistent
and aligned with the surrounding template syntax.
This commit is contained in:
Bowen Han 2025-09-15 23:59:19 -07:00 committed by GitHub
parent 51abc96bdc
commit f1fbffb5c0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.clang-format
View File

@ -22,6 +22,13 @@ AllowShortIfStatementsOnASingleLine: Never
AllowShortLambdasOnASingleLine: Inline AllowShortLambdasOnASingleLine: Inline
AllowShortLoopsOnASingleLine: false AllowShortLoopsOnASingleLine: false
AlwaysBreakBeforeMultilineStrings: true AlwaysBreakBeforeMultilineStrings: true
# Treat CUDA keywords/attributes as "attribute macros" and avoid breaking lines inside them
AttributeMacros:
- __host__
- __device__
- __global__
- __forceinline__
- __launch_bounds__
BinPackArguments: true BinPackArguments: true
BinPackParameters: false # OnePerLine BinPackParameters: false # OnePerLine
BitFieldColonSpacing: Both BitFieldColonSpacing: Both