Text Generation Web UI Files

Changes

• Replace use_flash_attention_2/use_eager_attention with a unified attn_implementation in the Transformers loader
• Ignore add_bos_token in instruct prompts, let the jinja2 template decide
• Add a "None" option for the speculative decoding model

Backend updates

• Update llama.cpp to https://github.com/ggml-org/llama.cpp/tree/90083283ec254fa8d33897746dea229aee401b37
• Update Transformers to 4.53
• Also update bitsandbytes/Accelerate/PEFT to the latest versions
• Update ExLlamaV3 to 0.0.5
• Update ExLlamaV2 to 0.3.2

Portable builds

Below you can find portable builds: self-contained packages that work with GGUF models (llama.cpp) and require no installation! Just download the right version for your system, unzip, and run.

Which version to download:

• Windows/Linux:
• NVIDIA GPU: Use cuda12.4 for newer GPUs or cuda11.7 for older GPUs and systems with older drivers.
• AMD/Intel GPU: Use vulkan builds.

• CPU only: Use cpu builds.

• Mac:

• Apple Silicon: Use macos-arm64.
• Intel CPU: Use macos-x86_64.

Updating a portable install:

1. Download and unzip the latest version.
2. Replace the user_data folder with the one in your existing install. All your settings and models will be moved.