Loading
Loading page content.Loading
Loading page content.Archive / 2026-09-20
<details open> CUDA: tune FA for Gemma 4 on Ampere or newer (#29152) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/48802880> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.c…
github.com1 month agoView details
langchain-ai/langchain langchain-typesafe==0.0.1a3
Initial release release(typesafe): 0.0.1a3 (#40693) feat(typesafe): make classifier questions invocation-scoped (#40659) release(typesafe): bump to 0.0.1a2 (#40576) feat(typesafe): experimental `AutoModeMiddleware` (#40545) feat(typesafe): experimental `ModelRouterMiddleware` (#…
github.com1 month agoView details
<details open> metal : support arbitrary hc in dsv4_hc_pre (#29169) the dsv4_hc_pre kernels hardcoded hc = 4 via a constexpr used with simd_shuffle, so the op was rejected by supports_op for any other hc and fell back to CPU. Kimi-K3 uses dsv4_hc_pre with hc equal to the number…
github.com1 month agoView details
<details open> fix(mamba) : make time-step projection input contiguous (#28832) * mamba : make time-step projection input contiguous Assisted-by: ChatGPT * mamba : skip contiguous copy after normalization Assisted-by: ChatGPT </details> **Website:** - <https://llama.app> **Attes…
github.com1 month agoView details
<details open> metal: add F16 input to the FWHT (#29094) * metal: add F16 input to the FWHT The Metal FWHT kernel accepts F32 input only. This change makes the source type a template parameter, so the kernel reads an F16 source directly instead of requiring a converted copy. The…
github.com1 month agoView details