NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
Go modules
Go modules, #2373 by repository stars
Latest stable
v1.32.0
Last release 14 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Nothing withdrawn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
Nothing published for this version
llama: add GGMLTypeF8_E4M3 and bump GGMLTypeCOUNT to 44 by @deadprogram in #477
Full Changelog: v1.31.0...v1.32.0
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.31.0...v1.32.0
Nothing published for this version
benchmarks: update the results for yzma 1.30.0 by @deadprogram in #461
Full Changelog: v1.30.0...v1.31.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.30.0...v1.31.0
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
Nothing published for this version
Nothing published for this version
Nothing published for this version
download: use newest nightly build again after the release by @deadprogram in #452
Full Changelog: v1.29.1...v1.30.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.29.1...v1.30.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
llamawasm: return the named template from ModelChatTemplate by @deadprogram in #450
Full Changelog: v1.29.0...v1.29.1
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.29.0...v1.29.1
Nothing published for this version
llama, mtmd: mark SetWarmup and Encode as deprecated by @deadprogram in #394
Full Changelog: v1.28.0...v1.29.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.28.0...v1.29.0
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
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
Nothing published for this version
Nothing published for this version
Nothing published for this version
download: use the newest nightly build again after the release by @deadprogram in #351
Full Changelog: v1.27.0...v1.28.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.27.0...v1.28.0
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
Nothing published for this version
Nothing published for this version
download: use newest nightly llama.cpp build again by @deadprogram in #338
Full Changelog: v1.26.1...v1.27.0
Full Changelog: https://github.com/hybridgroup/yzma/compare/v1.26.1...v1.27.0
Nothing published for this version
Nothing published for this version
This release makes a check of an installation work without a network.
This release makes a check of an installation work without a network.
Install keeps the digest manifest beside the install record,yzma-manifest.json, and puts the digest of it in the record. yzma verify readsyzma installs llama.cpp v0.4.0--version latest to get the mostFull Changelog: v1.26.0...v1.26.1
Nothing published for this version
This release lets yzma run in a browser, and it checks what it installs.
This release lets yzma run in a browser, and it checks what it installs.
llama.cpp becomes a WebAssembly module, and a Go program compiledpkg/llamawasm package. There are three builds,pkg/llama andpkg/mtmd. See wasm/README.md.Install checks the SHA-256 of each file against the manifest thatllama-cpp-builder publishes. A version takes the form VERSION@sha256:DIGEST to pinyzma verify command checks an installation later.yzma installs llama.cpp v0.4.0 when--version latest to get the most recent nightly build.mtmd gets TokenizeFromParts and InputPart, and llama gets a wrapper forllama_sampler_init_temp.Full Changelog: v1.25.0...v1.26.0
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
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
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.