nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity
7,026 Commits 1 Branch 0 Tags
3fe36c32389ade876ec505f32df08f5121cf597f
Commit Graph
3 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Gian-Carlo PascuttoandGitHub 1e19f5d462 common : Add top-nsigma sampler to help globally (#15428) 
Fixes #15423.
 2025-08-19 19:58:14 +03:00
Gian-Carlo PascuttoGitHubGeorgi Gerganov
 		58d07a8043 metal : copy kernels for quant to F32/F16 conversions (#12017) 
metal: use dequantize_q templates

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-02-25 11:27:58 +02:00
Gian-Carlo PascuttoandGitHub d70908421f cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#12000) 2025-02-22 09:43:24 +01:00