Loading
Loading
v0.35.1 · · Maintenance release, see changelog
b11372 · · Halve the indexer score memory qwen4exp: halve the indexer score memory The indexer scored all heads in one product and rectified a copy of it, so two [npool, nidxh, ntokens] f32 tensors were live at once, the largest buffers of the graph at long context
v0.30.0 · · New models: DeepSeek-V4.1-Flash with the whole KV stored in MXFP8 through the FlashMLA V4.1 record on SM100, DeepGEMM Mega-mHC, and async Engram prefetch with Engram DP…
· How to use Splash by Inco AI in LM Studio Bionic
v2026.9.8 · · OpenClaw 2026.9.8 adds GPT-6.1 Sol as a model choice through the OpenAI provider for accounts with access. It keeps delegated results tied to the conversation that requested…
· Two bots for the last mile of shipping code: Rollouts watches every change as it deploys, and Security Review reports exploitable bugs on every pull request.
v2.1.288 · · Added $.ui.selection for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row
rust-v0.160.0 · · Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. · Preview rust-v0.162.0-alpha.8 (alpha)
v0.86.0 · · Added support for all GPT-5 models.
n8n 2.41.6 · · Keep the task runner running on an unhandled promise rejection