Releases · Emreerdog/mbase

2 min read Original article ↗

v0.3.1

MBASE SDK Release

v0.3.1 Latest - 2025-06-26

SDK Fix

  • MBASE server application now working on windows fixed.

  • important fix on processor update_t loop 1fc6b66

SDK Added

v0.3.0

MBASE SDK Release

v0.3.0 Latest - 2025-06-11

SDK Fix

SDK Added

  • MBASE MCP library has been implemented

  • mbase::subprocess class is implemented 19fcb20, cfe5b4d

  • Added a special _read_stdin method to io_file object 29a649d

v0.2.5

MBASE SDK Release

v0.2.5 Latest - 2025-05-04

SDK Fix

SDK Added

  • In json library, const getters are implemented fa32029

  • STD file handles can be accessed through io_file objects now ddb7fe0

  • llama logger is disabled by default now 74deca7

v0.2.4

MBASE SDK Release

v0.2.4 Latest - 2025-04-06

SDK Fix

  • In simple-conversation program, #include <locale.h> changed to #include <clocale>. Former was causing compiler errors on macOS. f782666

  • llama kv cache methods names are updated. 0ab7b66

  • Fixed a problem in io_file.h file which were causing compiler errors on windows. e64c869

  • Phi model template fixed. 124e9d2

SDK Added

  • File operations were only accepting wide strings, now they also accept multibyte strings. 7c67a55

  • Implemented mbase::max_element and mbase::min_element. d188bc1

v0.2.3

v0.2.2

v0.2.1

Release Notes

  • In decode behavior description, remove the halt delay and work with mutexes. -> f3e924f
  • Fixed a major bug in vector and string erase method in which was causing std::bad_alloc exception.

About Pre-compiled Binaries

The precompiled binaries can't be provided for now due to some incorrectness in project configuration.

Refer to compiling from source: https://docs.mbasesoftware.com/inference/quickstart/setup/compile_from_source

v0.2.0

Release Notes

  • Write safer is_float, is_number ... methods in mbase::string -> 7d385b1
  • Implement processor unregistration. -> 3267bb1
  • Processor LoRA implementation is missing. -> a8f4406

API Changes

  • mbase::vector<inf_lora_adapter> get_adapters() const; method implemented in InfModelTextToText.
  • I32 get_cache_token_count() const;, method implemented in InfProcessorTextToText. By this, users will be able to see how many tokens are in the kv cache.
  • LoRA operations are implemented.

About Pre-compiled Binaries

The precompiled binaries can't be provided for now due to some incorrectness in project configuration.

Refer to compiling from source: https://docs.mbasesoftware.com/inference/quickstart/setup/compile_from_source

First release