Backfill issue -228 — The AI Toolchain

EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW

ISSUE VIEW full issue

Do you prefer this view?

$ tct list   # 4 tools matched

AI & LLM Tooling

◆ AI Coding Agents

SST OpenCode

v1.0.222 NOTES

The open source coding agent.

OpenCode v1.0.222 adds Windows PTY support, in-app update toasts, and subagent mentions in the desktop app.

└──▷ GET THIS VERSION

$ git clone --branch v1.0.222 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.222

›Adds Windows support for PTY and cross-platform build scripts in the desktop application.
›Adds in-app update toasts to the desktop application.
›Adds subagent mention support to the desktop application.

Was this useful?

Alibaba Qwen Code

v0.6.0-nightly.20260101.105ad743 NOTES

Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and ChatCompletionContentPart merging support.

└──▷ GET THIS VERSION

$ git clone --branch v0.6.0-nightly.20260101.105ad743 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.6.0-nightly.20260101.105ad743

›Adds support for merging ChatCompletionContentPart items and filters empty messages in chat completion handling.
›Auto-detects LLM output language from the system locale, eliminating the need to manually configure response language.

Was this useful?

◆ Local LLM Runtimes

SGLang

v0.5.7 NOTES

SGLang v0.5.7 adds day-0 support for Mimo-V2-Flash, LLaDA 2.0, EAGLE 3 speculative decoding, Model Gateway v0.3.0, and --dit-layerwise-offload for diffusion models.

└──▷ GET THIS VERSION

$ git clone --branch v0.5.7 https://github.com/sgl-project/sglang.git
# already have the repo? check out this version:
$ git checkout v0.5.7

└──▷ TRY IT

Reduce peak VRAM by up to 30 GB when serving a diffusion model on a memory-constrained GPU.

$ python -m sglang.launch_server --model-path <diffusion-model-path> --dit-layerwise-offload true

Override protected sampling fields and control frame count when generating video with the diffusion CLI.

$ python -m sglang.diffusion.cli --model-path <diffusion-model-path> --adjust-frames 16 --override-protected-fields

›Adds --dit-layerwise-offload true CLI flag for SGLang-Diffusion to reduce peak VRAM usage by up to 30 GB and improve performance by up to 58% across all diffusion models.
›Adds --adjust-frames and --override-protected-fields CLI arguments to the diffusion pipeline.
›Day-0 support for Mimo-V2-Flash, Nemotron-Nano-v3, and LLaDA 2.0 models.
›Day-0 support for Qwen-Image-Edit-2509, Qwen-Image-Edit-2511, Qwen-Image-2512, and Qwen-Image-Layered in SGLang-Diffusion.
›Releases Model Gateway v0.3.0 with multimodal initialization and image processors for LLaVA, Qwen2-VL, Qwen2.5-VL, Qwen3-VL, Phi3-Vision, Phi4-Vision, LLaMA-4-Vision, and Mistral 3.

+15 moreshow less

›EAGLE 3 speculative decoding draft models now available for popular models.
›Adds scalable pipeline parallelism with dynamic chunking for ultra-long contexts.
›Adds encoder disaggregation support for multi-modal models.
›Enables RadixCache for Mamba2 models.
›Supports pipeline parallelism (PP) combined with PD decode disaggregation via the nixl backend.
›Adds MXFP8 Grouped GEMM support on Blackwell (B200) GPUs via sgl-kernel.
›Adds Cache-dit integration for SGLang-Diffusion to improve performance by up to 165%.
›Extends SGLang-Diffusion to support AMD, RTX 4090, and RTX 5090 GPUs, additional attention backends (sage-attn, sage-attn3), tensor parallelism (TP), and Google Vertex AI in the HTTP API.
›Adds single-batch overlap for MoE models to improve throughput.
›Adds Mistral Large 3 and Mistral Large 3 EAGLE speculative decoding support.
›Adds Ministral 3 model support.
›Supports data-parallelism for GLM-V vision models.
›Adds configurable generator device and seed support for the diffusion HTTP API.
›Adds a lightweight runtime Docker stage via Dockerfile refactor.
›Adds model architecture and type fields to the server info endpoint for gateway harmony.

Was this useful?

llama.cpp

b7607 3 RELEASES · 2026-01-01 NOTES STABLE

llama.cpp b7607 adds support for the Youtu-VL vision-language model.

└──▷ GET THIS VERSION

$ git clone --branch b7607 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7607

›Adds support for the Youtu-VL vision-language model.

2 more releases in this issue · 2026-01-01

b7605 NOTES STABLE

llama.cpp b7605 adds support for JinaBertModel with non-gated feed-forward networks, including German tokenizer variant.

└──▷ GET THIS VERSION

$ git clone --branch b7605 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7605

›Adds support for JinaBertModel with non-gated (standard GELU) feed-forward network variant, detected automatically from tensor dimensions.
›Adds jina-v2-de tokenizer variant in the converter to support the German Semantic V3 model.

b7603 NOTES STABLE

llama.cpp b7603 adds support for the Solar-Open model with chat template and reasoning tags.

└──▷ GET THIS VERSION

$ git clone --branch b7603 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7603

›Adds support for the Solar-Open model, including its LLM type, vocabulary end-of-generation handling, and a solar-open chat template in llama-chat.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · January 1, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -228, January 1, 2026

SST OpenCode

Alibaba Qwen Code

SGLang

llama.cpp