tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : fix mirostat state when using multiple sequences (#3543)

Browse Source 
* Fix mirostat state when using multiple sequences

* Fix mirostat by completely refactoring sampling!

* Try to fix zig build.

* Export function to fetch/create default sampler states

Code formatting cleanups and add some comments

Silence a warning about id not being used when logging is disabled

* Apply some renaming suggestions.

Fix comments that were out of sync with the pull.

* Use more consistant naming convention for sampling contexts
This commit is contained in:
Kerfuffle
2023-10-11 13:35:46 -06:00
committed by GitHub
parent 8c70a5ff25
commit 70c29da118
14 changed files with 495 additions and 334 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/CMakeLists.txt
View File

@ -5,6 +5,8 @@ set(TARGET common)
add_library(${TARGET} OBJECT
common.h
common.cpp
sampling.h
sampling.cpp
console.h
console.cpp
grammar-parser.h