cli : load backends after validating input files - #4069
Merged
Merged
Conversation
Co-authored-by: Cursor <cursoragent@cursor.com>
danbev
approved these changes
Sep 18, 2026
Co-authored-by: Cursor <cursoragent@cursor.com>
danbev
approved these changes
Sep 18, 2026
Member
|
The failing android CI jobs were fixed as part of 4afa009. |
bygreencn
added a commit
to bygreencn/whisper.cpp
that referenced
this pull request
Sep 23, 2026
* ggerganov/master: (81 commits) fix(yt-wsp): Resolve script path without GNU realpath (ggml-org#4072) cli : load backends after validating input files (ggml-org#4069) ci : update android-actions to v4.0.4 (ggml-org#4074) docs : clarify VAD mode timestamps and CWD model path errors (ggml-org#4019) readme : document the ANEForge encoder backend (ggml-org#4073) whisper : optional ANEForge encoder backend (Apple Neural Engine) (ggml-org#3905) whisper : fix int overflow in whisper_full_parallel chunk offsets (ggml-org#4044) sync : ggml ggml : bump version to 0.24.0 (ggml/1627) tests(s390x): add non-vxe build to tests (llama/28776) sycl: rfc: Use radix select for top_k (llama/28670) ggml-cpu : disable PCH and fix CACHE_LINE_SIZE ambiguity to fix heap corruption (llama/28882) sycl : fix oneDNN scratchpad breaking the pool free order (llama/28704) ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (llama/28846) ggml-cpu(s390x): guard VXE-only repack helpers (llama/28775) sycl : Fix get mem error (llama/28227) vulkan: workaround NV queuesubmit driver bug (llama/28830) opencl: apply the noshuffle row-alignment rule to q4_K, q5_K and q8_0, not just q6_K (llama/28575) ggml-cuda: hip add specific config table for AMD GCN (llama/27841) syscl : Handle (fail gracefully) unsupported tq1_0 quants (llama/28681) ...
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I noticed that expensive operations (e.g., compiling shaders) are done prior to checking if the input file even exists.
Solution:
Note
AI assistant used to locate the call and apply the move. I can discuss the change.
Made with Cursor