llama_cpp_for_radxa_dragon_.../common
Georgi Gerganov 644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
* sampling : refactor + optimize penalties sampler

ggml-ci

* common : apply ignore_eos as logit bias

ggml-ci

* batched : remove penalties sampler

* params : allow penalty_last_n == -1 to be equal to context size

ggml-ci

* common : by default, move the penalties at the end of the sampling chain

ggml-ci

* common : ignore all EOG tokens

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* common : move back the penalties at the front of the sampling chain

ggml-ci

* readme : restore hint about --ignore-eos flag [no ci]

* llama : minor

ggml-ci

* webui : update

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-16 12:31:14 +02:00
..
cmake
arg.cpp sampling : refactor + optimize penalties sampler (#10803) 2024-12-16 12:31:14 +02:00
arg.h
base64.hpp
build-info.cpp.in
CMakeLists.txt Opt class for positional argument handling (#10508) 2024-12-13 19:34:25 +01:00
common.cpp sampling : refactor + optimize penalties sampler (#10803) 2024-12-16 12:31:14 +02:00
common.h sampling : refactor + optimize penalties sampler (#10803) 2024-12-16 12:31:14 +02:00
console.cpp
console.h
json-schema-to-grammar.cpp
json-schema-to-grammar.h
json.hpp
log.cpp
log.h
ngram-cache.cpp
ngram-cache.h
sampling.cpp sampling : refactor + optimize penalties sampler (#10803) 2024-12-16 12:31:14 +02:00
sampling.h
speculative.cpp server : fix free of spec context and batch (#10651) 2024-12-07 11:52:44 +02:00
speculative.h
stb_image.h