Skip to content

Releases: cpumaxx/llama.cpp

b2794

06 May 01:08
@github-actions github-actions
b2794
628b299
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
b2794 Latest
Latest 
Adding support for the --numa argument for llama-bench. (#7080)
Assets 19

b2792

05 May 07:17
@github-actions github-actions
b2792
ca36326
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
b2792 
readme : add note that LLaMA 3 is not supported with convert.py (#7065)
Assets 19
Loading

b2755

29 Apr 00:50
@github-actions github-actions
b2755
e00b4a8
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
b2755 
Fix more int overflow during quant (PPL/CUDA). (#6563)

* Fix more int overflow during quant.

* Fix some more int overflow in softmax.

* Revert back to int64_t.
Assets 18
Loading