vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-11 09:25:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
koboldcpp/examples/speculative
History
Exact
Gaurav Garg dd1ea52433
llama : support multi-output backend sampling (#25532) 
* Enable backend sampling with token speculation

* Clamp the mask sum before converting it into the sampled index

* Add a numeric context parameter declaring the maximum outputs one sequence

* More fixes

* Don't reuse memory for output views.

* Match dist between CPU and GPU

* Fix CPU and backend sampling mismatches

* Simpify some of the changes

* Fix tests on Vulkan

* More test fixes

* Rebase changes

* Rebase and address review comments

* Address review comments

* Address review comments

* Update src/llama-sampler.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-08-10 16:58:56 +03:00
..
CMakeLists.txt libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
README.md repo : update links to new url (#11886) 2025-02-15 16:40:57 +02:00
speculative.cpp llama : support multi-output backend sampling (#25532) 2026-08-10 16:58:56 +03:00

README.md

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info: