ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-12 06:50:08 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,104 Commits 755 Branches 1 Tag
c03ee1a4d297840ea91ee9ffde6e402a9e993b42
Commit Graph

5 Commits

Author SHA1 Message Date
dungquixote42
52ad1c6421 Implement Adaptive-P Sampler (#1100) 
* initial implementation of adaptive-p sampler

* explicitly mark candidates unsorted + cleanup qualifiers

* cosmetic update

* reorg prototypes

* lockstep with mainline

* add _impl for _init + reorg

* add LLAMA_API to prototypes

* update sharpness to 10

* lockstep: rng seed

* delete llama_sampling member in llama_sampler_adaptive_p

* fix LLAMA_API return type

* lockstep: rng seed cont

* actually correct implementation

* lockstep: sorting behavior

* const -> constexpr for known constants

* add missing space

* fix softmax usage in adaptive p sampler

* cosmetic changes

* implement do-not-sort version of softmax

* simpify rng seed, add static to constexpr

* refactor: remove iface + use shared rng + use actually original probabilities

* adaptive-p: add dedicated rng back in

* fix initial max_logit + add float vector to adaptive p sampler context + stochastic sampling

* adaptive-p: fuse first softmax with transformation

* adaptive-p: implement binary search selection

* adaptive-p: update comment
 2026-01-10 07:58:53 +02:00
firecoperana
d1f92e24d3 add dry sampler (#513) 
* add dry sampler

* use vocab instead of model in dry_init function

* fix compile error for build test

---------

Co-authored-by: firecoperana <firecoperana>
 2025-06-19 10:24:53 +03:00
Kawrakow
1d28b2a9a1 Adding top-n-sigma sampler (#489) 
* Adding top-n-sigma sampler

* Fix typos in XTC PR

* Update README.md for main and server

* More README

* More README

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2025-06-03 17:35:09 +03:00
Kawrakow
accf69b126 Adding the XTC sampler (#486) 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2025-06-03 11:32:03 +03:00
Kawrakow
0ceeb11721 Merge mainline llama.cpp (#3) 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 2024-07-27 07:55:01 +02:00