Skip to content

Update submodules #1

New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Jump to bottom
Closed
1 task
iboB opened this issue Nov 18, 2024 · 9 comments · Fixed by #16
Closed
1 task

Update submodules #1

iboB opened this issue Nov 18, 2024 · 9 comments · Fixed by #16
Assignees
@pminev

Comments

@iboB
Copy link
Member

iboB commented Nov 18, 2024

It's time to update our forks and submodules. Check for upstream updates and merge them if necessary.

Don't forget to use the guide.

Subbmodules to update:

  • llama.cpp
@iboB iboB self-assigned this Nov 18, 2024
@pminev
Copy link
Contributor

pminev commented Dec 4, 2024

llama_sampler_init_tail_free is removed. See the PR.

@pminev pminev mentioned this issue Dec 4, 2024
Merged
@pminev
Copy link
Contributor

pminev commented Dec 4, 2024 •
edited
Loading

Added support for IBM's granite chat template in this commit. Maybe we should add it to the tests?

@pminev
Copy link
Contributor

pminev commented Dec 4, 2024

Enabled KV cache defrag by default. Commit

@pminev
Copy link
Contributor

pminev commented Dec 4, 2024

KV cache state is reverted in case of failed compute

commit

@pminev
Copy link
Contributor

pminev commented Dec 4, 2024

OLMo November 2024 support - commit

@pminev
Copy link
Contributor

pminev commented Dec 4, 2024

new api llama_kv_cache_can_shift in this commit

@pminev
Copy link
Contributor

pminev commented Dec 4, 2024

Now we can pass multiple devices to the model - commit

@pminev
Copy link
Contributor

pminev commented Dec 4, 2024

Enabled cache prompt by default - commit

@pminev
Copy link
Contributor

pminev commented Dec 5, 2024

Exposed new API llama_chat_builtin_templates for suppoted chat templates

@iboB iboB assigned pminev and unassigned iboB Dec 5, 2024
@pminev pminev closed this as completed in #16 Dec 5, 2024
@github-project-automation github-project-automation bot moved this from Todo to Done in Local SDK Beta Dec 5, 2024
# for free to join this conversation on GitHub. Already have an account? # to comment
Assignees

@pminev pminev

Labels
None yet
Projects
Local SDK Beta
Status: Done
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Update llama.cpp alpaca-core/ilib-llama.cpp
2 participants
@iboB @pminev