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.
-
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 sourcegithub.com -
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 sourcegithub.com -
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 sourcegithub.com -
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 sourcegithub.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.