whisper : load the model into multiple buffers of max size 1GB #1763
Conversation
This file contains 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
bygreencn
added a commit
to bygreencn/whisper.cpp
that referenced
this pull request
Jan 16, 2024
* ggerganov/master: (86 commits) server : fix building and simplify lib deps on Windows (ggerganov#1772) talk-llama : sync llama.cpp talk-llama : llama.cpp sync : ggml metal : correctly set SIMD support flags on iOS (llama/4923) 2-bit quantizations (llama/4897) scripts : sync-ggml-am.sh add option to skip commits talk-llama : sync llama.cpp sync : ggml examples : adapt to metal API ggml: cache sin/cos for RoPE (llama/4908) metal : remove old API (llama/4919) metal : disable log for loaded kernels (llama/4794) gguf : fix potential infinite for-loop (llama/4600) metal : refactor kernel loading code (llama/4794) CUDA: faster q8_0 -> f16 dequantization (llama/4895) talk-llama : add optional CLI arg to set the bot name (ggerganov#1764) examples : add python example for transcription (ggerganov#1744) whisper : load the model into multiple buffers of max size 1GB (ggerganov#1763) talk-llama : sync llama.cpp ...
jiahansu
pushed a commit
to WiseSync/whisper.cpp
that referenced
this pull request
Apr 17, 2024
viktor-silakov
pushed a commit
to viktor-silakov/whisper_node_mic.cpp
that referenced
this pull request
May 11, 2024
iThalay
pushed a commit
to iThalay/whisper.cpp
that referenced
this pull request
Sep 23, 2024
iThalay
pushed a commit
to iThalay/whisper.cpp
that referenced
this pull request
Sep 23, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
ref ggerganov/ggml#647
This solves the problem with the 1GB limit per buffer for iOS devices.
The fix can serve as an example of how to split a large buffer (for example the one containing the model weights) into multiple smaller buffers with a certain maximum size