NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
Go modules, #2373 by repository stars
Latest stable
v1.32.0
Last release 13 days ago
07 Nov 2026
Ships on a steady schedule
a new release about every 1 weeks
Nearly every release is documented
notes for 52 of 52 stable releases
Nothing withdrawn
no release was ever pulled
1 years old
197 releases · first in 2025
Drag across the ruler to compare, or tap a release to open it.
Nothing published for this version
download: support the new llama.cpp tagged releases by @deadprogram in #297
Full Changelog: v1.24.0...v1.25.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.24.0...v1.25.0
Your coding agent can read these notes before it upgrades. Set up the MCP server →
llama: bind the ggml backend device accessors for device detection by @deadprogram in #294
Full Changelog: v1.23.0...v1.24.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.23.0...v1.24.0
yzma-checker: add a standalone FFI type-contract auditor by @dlsniper in #283
Full Changelog: v1.22.0...v1.23.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.22.0...v1.23.0
llama: add LoadMTP to ModelParams for llama.cpp b10212+ by @deadprogram in #281
Full Changelog: v1.21.0...v1.22.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.21.0...v1.22.0
llama: correct LoadMode values for current llama.cpp by @samyfodil in #278
Full Changelog: v1.20.0...v1.21.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.20.0...v1.21.0
switched to use CUDA 13.3 for Windows llama.cpp by @kaleah08 in #273
Full Changelog: v1.19.0...v1.20.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.19.0...v1.20.0
Nothing published for this version
mtmd: add new TextLen field to mtmd.InputText by @deadprogram in #268
Full Changelog: v1.18.0...v1.19.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.18.0...v1.19.0
test: check for any valid chunk since return order may be different by @deadprogram in #261
Full Changelog: v1.17.1...v1.18.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.17.1...v1.18.0
mtmd: add BatchMaxTokens for new field added by llama.cpp by @deadprogram in #260
Full Changelog: v1.17.0...v1.17.1
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.17.0...v1.17.1
mtmd: modify Bitmap file helpers to return new BitmapWrapper by @deadprogram in #259
Full Changelog: v1.16.1...v1.17.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.16.1...v1.17.0
context: add new parent context for MTP support added in llama.cpp by @deadprogram in #257
Full Changelog: v1.16.0...v1.16.1
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.16.0...v1.16.1
mtmd: update bitmap helpers for llama.cpp PR #23913 placeholder support by @deadprogram in https://github.com/hybridgroup/yzma/pull/256
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.15.0...v1.16.0
addition: limit max outputs of llama_context by @deadprogram in https://github.com/hybridgroup/yzma/pull/255
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.14.1...v1.15.0
pkg/llama: add llama_n_rs_seq binding by @deadprogram in https://github.com/hybridgroup/yzma/pull/252
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.14.0...v1.14.1
ci,download: replace GitHub API with static version endpoint by @deadprogram in https://github.com/hybridgroup/yzma/pull/241
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.13.0...v1.14.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
llama: remove llama_params_fit and llama_memory_breakdown_print bindings by @deadprogram in https://github.com/hybridgroup/yzma/pull/239
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.12.0...v1.13.0
build: use the latest binary from llama-cpp-builder for latest test builds by @deadprogram in https://github.com/hybridgroup/yzma/pull/235
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.11.1...v1.12.0
feature: use hybridgroup/llama-cpp-builder as source of version for most recent llama.cpp build by @deadprogram in https://github.com/hybridgroup/yzma
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.11.0...v1.11.1
Add ROCm backend support by @dlsniper in https://github.com/hybridgroup/yzma/pull/219
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.10.0...v1.11.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
docs: a few small improvements by @deadprogram in https://github.com/hybridgroup/yzma/pull/210
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.9.0...v1.10.0
Nothing published for this version
download: remove deprecated functions and add AlreadyInstalled() by @deadprogram in https://github.com/hybridgroup/yzma/pull/205
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.8.0...v1.9.0
Nothing published for this version
benchmarks: Benchmark updates by @deadprogram in https://github.com/hybridgroup/yzma/pull/189
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.7.0...v1.8.0
feature: add Batch helper functions for #165 by @deadprogram in https://github.com/hybridgroup/yzma/pull/178
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.6.0...v1.7.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
Add many missing or new llama.cpp functions by @dlsniper in https://github.com/hybridgroup/yzma/pull/174
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.5.1...v1.6.0
Nothing published for this version
Nothing published for this version
mtmd: add new members to mtmd.ContextParamsType from llama.cpp #17914 by @deadprogram in https://github.com/hybridgroup/yzma/pull/170
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.5.0...v1.5.1
Nothing published for this version
Collection of small fixes by @dlsniper in https://github.com/hybridgroup/yzma/pull/161
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.4.1...v1.5.0
Nothing published for this version
Nothing published for this version
llama: add new experimental context params from llama.cpp by @deadprogram in https://github.com/hybridgroup/yzma/pull/159
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.4.0...v1.4.1
feature: load model from split files by @deadprogram in https://github.com/hybridgroup/yzma/pull/156
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.3.0...v1.4.0
Nothing published for this version
chore: change media marker location to start of prompt to match behavior in llama.cpp by @deadprogram in https://github.com/hybridgroup/yzma/pull/152
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.2.0...v1.3.0
Nothing published for this version
download: use CUDA 13 builds for Windows and Linux amd64/arm64 by @deadprogram in https://github.com/hybridgroup/yzma/pull/149
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.1.0...v1.2.0
Nothing published for this version
feature: update gonja and disable extra logging by @deadprogram in https://github.com/hybridgroup/yzma/pull/139
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.0.1...v1.1.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
fix: modify extraction of llama.cpp archive by @deadprogram in https://github.com/hybridgroup/yzma/pull/138
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.0.0...v1.0.1
One column per month.