zapret Releases
73 releases of bol-van/zapret
- v69.4
Improves DPI desync by wrapping both segments in fakedsplit and fakedisorder modes, and allows users to specify custom fake content patterns via a new command-line option.
Dec 2, 2024
- v69.3
Introduces fixed hostlist and ipset parameters that cannot be changed after launch, adds build metadata (release number, commit hash, SHA256 sums), and creates a lightweight version for OpenWrt.
Nov 24, 2024
- v69.2
Adds a `--skip` parameter to temporarily exclude a profile without deleting settings, a `--methodeol` flag to fix HTTP header formatting, and fixes pgrep compatibility for busybox systems.
Nov 23, 2024
- v69.1
This is a maintenance release addressing logic errors in hostlist processing for tpws and providing a specific patch for Keenetic routers.
Nov 22, 2024
- v69
This release introduces advanced DPI desync strategies (multisplit, multidisorder), renames several parameters, adds Android support, and refines the blockcheck tool.
Nov 19, 2024
- v68
This release focuses on documentation improvements (Markdown for Russian docs), new configuration file syntax, and enhancements to installation scripts for OpenWrt.
Nov 8, 2024
- v67
This release introduces host-list deduplication and auto-reload, DoH support in mdig and blockcheck, and significant updates to Windows binaries including UPX compression.
Nov 1, 2024
- v66
A major architectural overhaul of the startup system for Linux, OpenWrt, and MacOS. Existing configurations are incompatible, and new minimal startup scripts for OpenWrt are provided.
Oct 29, 2024
- 0.1.2v0.1.2
Minimal release notes: "- Added `autoawq` model family - Published multiple docker images supporting multiple BLAS backends (llama.cpp) - Remo"
Nov 13, 2023
- 0.1.1v0.1.1
Minimal release notes: "- Upgrade llama-cpp-python to support GGUF format - Upgrades to GPTQ-for-LLama related libs - Update README.md"
Oct 25, 2023
- 0.1.0v0.1.0
This initial release introduces support for Hugging Face generic models and upgrades llama.cpp to enable Llama 2 compatibility. It also optimizes the deployment by streamlining Docker images into a lightweight default and a GPU-enabled version. Additionally, it includes general stability fixes.
Jul 23, 2023
- 0.0.4-gptq-llama-tritonv0.0.4-gptq-llama-triton
Minimal release notes: "- Separate models in their own sub directories to prevent overriding configs when changing models - Add triton support"
Jun 16, 2023
- 0.0.4v0.0.4
Minimal release notes: "- Separate models in their own sub directories to prevent overriding configs when changing models"
Jun 8, 2023