DigestAI news desk

Cut through the AI noise.

Model

Qwen4Exp news

The latest Qwen4Exp news, : Ggml-org adds fused top‑k mask operation to llama.cpp.

Qwen4exp is an AI model supported by the llama.cpp repository, featuring high-capacity operations and a Mixture of Token Predictors architecture. Recent updates introduce MTP speculative decoding for a 1.5x speedup, fused Vulkan kernels for specific operations, and a fused top-k mask node for the CUDA backend.

4 stories mentioning Qwen4Exp since 28 September 2026, newest first, each with its sources and discussion. Follow to see new ones on your front page.

  1. Research new

    Ggml-org adds fused top‑k mask operation to llama.cpp

    A pull request to the ggml‑org/llama.cpp repository introduces a new fused operation for QSA masking. The change adds the GGMLOPTOPKMASK node to the CUDA backend, allowing the mask to be applied per‑head with optional…

    1 source primary source
    github.com
  2. Research new

    Llama.cpp adds MTP decoding for Qwen4Exp and GLM-5.3-Flash hybrid model

    llama.cpp version 0.6.0 introduces MTP (Mixture of Token Predictors) speculative decoding for the Qwen4Exp model, claiming a ~1.5x speedup on DGX Spark hardware. The update also adds support for the GLM-5.3-Flash…

    2 sources primary source
    github.com
  3. Research new

    Qwen4Exp adds MTP support in llama.cpp pull request

    A pull request merged into the llama.cpp repository on October 1, 2026, adds support for MTP (likely referring to Mixture of Token Predictions or a similar technique) to the Qwen4Exp model. The change was approved by…

    2 sources primary source
    github.com
  4. Hardware & Compute new

    Ggml-org merges Vulkan kernel fusion for Qwen4exp's SCALE‑sigmoid‑SCALE chain

    A pull request (29520) was merged into the ggml‑org/llama.cpp repository on Sep 28 2026, adding a fused Vulkan kernel that combines the SCALE‑SIGMOID‑SCALE‑hcpost operations used by the Qwen4exp model. The change was…

    1 source primary source
    github.com

Questions about Qwen4Exp

What is the latest Qwen4Exp news?

As of 16 October 2026: Ggml-org adds fused top‑k mask operation to llama.cpp. A pull request to the ggml‑org/llama.cpp repository introduces a new fused operation for QSA masking.

What is Qwen4Exp?

Qwen4exp is an AI model supported by the llama.cpp repository, featuring high-capacity operations and a Mixture of Token Predictors architecture. Recent updates introduce MTP speculative decoding for a 1.5x speedup, fused Vulkan kernels for specific operations, and a fused top-k mask node for the CUDA backend.