feat: upgrade llama.cpp #645
Merged
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
wsxiaoys
commented
Oct 26, 2023
| @@ -21,7 +21,6 @@ class TextInferenceEngineImpl : public TextInferenceEngine { | |||
| TextInferenceEngineImpl(owned<llama_model> model, owned<llama_context> ctx) : | |||
| model_(std::move(model)), | |||
| ctx_(std::move(ctx)) { | |||
| batch_ = llama_batch_init(N_BATCH, 0); | |||
There was a problem hiding this comment.
Previous usage of batch api in tabby generates a segmentation fault with updated llama.cpp version - roll back to llama_batch_get_one as workaround, will revisit this when integrating the continuous batching support.
| @@ -89,4 +89,8 @@ impl ModelDir { | |||
| pub fn ggml_q8_0_file(&self) -> String { | |||
| self.path_string("ggml/q8_0.gguf") | |||
| } | |||
|
|
|||
| pub fn ggml_q8_0_v2_file(&self) -> String { | |||
There was a problem hiding this comment.
updated llama.cpp requires re-converting all starcoder models, updating filepath to keep forward compatibility.
wsxiaoys
force-pushed
the
upgrade-llama-cpp
branch
from
8e1690b to
00accd7
Compare
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Outdated suggestions cannot be applied.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.
this change will merge once we've updated gguf files for all models in https://tabby.tabbyml.com/docs/models/
fix TAB-281