Skip to content

Conversation

mochiya98
Copy link
Contributor

Add .gitignore entries for OpenVINO support.
This eliminates unexpected diffs when using OpenVINO.

# added
models/*-encoder-openvino.xml
models/*-encoder-openvino-cache/

for

whisper.cpp/src/whisper.cpp

Lines 3367 to 3376 in cead8f5

static std::string whisper_openvino_get_path_encoder(std::string path_bin) {
auto pos = path_bin.rfind('.');
if (pos != std::string::npos) {
path_bin = path_bin.substr(0, pos);
}
path_bin += "-encoder-openvino.xml";
return path_bin;
}

whisper.cpp/src/whisper.cpp

Lines 3378 to 3388 in cead8f5

static std::string whisper_openvino_get_path_cache(std::string path_bin) {
auto pos = path_bin.rfind('.');
if (pos != std::string::npos) {
path_bin = path_bin.substr(0, pos);
}
path_bin += "-encoder-openvino-cache";
return path_bin;
}
#endif

@danbev danbev merged commit a0d2c63 into ggml-org:master Jun 24, 2025
103 of 104 checks passed
@mochiya98 mochiya98 deleted the openvino-fix branch June 25, 2025 05:02
bygreencn added a commit to bygreencn/whisper.cpp that referenced this pull request Jun 29, 2025
* ggerganov/master: (72 commits)
  ci : use selective copy for musa image (ggml-org#3296)
  ci: set fail-fast to false in docker.yml (ggml-org#3294)
  ruby : add Whisper::VERSION (ggml-org#3292)
  whisper : add version function (ggml-org#3289)
  ci : add should_release variable (ggml-org#3288)
  docs : add cmake "-j" flag in README.md (ggml-org#3284)
  ci : add support for tag-based releases (ggml-org#3287)
  release : v1.7.6
  bench : update benches
  bench : print system info before ctx check
  stream : add nullptr check of whisper_context (ggml-org#3283)
  ci : enable main-cuda build (ggml-org#3282)
  bindings.java : update java example (ggml-org#3281)
  coreml : backport CoreML features to macos < 14 (ggml-org#3255)
  ci : reduce musa image size (ggml-org#3277)
  whisper : add .gitignore entries for OpenVINO support (ggml-org#3276)
  command: output commands to text file (ggml-org#3273)
  ci : add apt-get clean to musa Dockerfile (ggml-org#3275)
  ruby : specify Apple frameworks explicitly on build (ggml-org#3270)
  talk-llama : sync llama.cpp
  ...
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants