github llama.cpp · just now · inference

llama.cpp b11158 enables KHR cooperative matrix support for Adreno GPUs

from English

The llama.cpp project released build b11158, which includes a tune of KHR cooperative matrix support specifically for Adreno GPUs via the Vulkan backend.

Enabled cooperative matrix (coopmat) support for the Vulkan backend to improve performance on compatible hardware.
Fixed the mul_mat_s function within the implementation.
Removed debug statements from the codebase.

This update provides optimized GPU acceleration for Snapdragon devices running Linux and Android, as well as Windows arm64 systems with Adreno graphics.

Importance 1/3 Trust 1/3 llama.cpp Hugging Face Inference efficiency

Read original

github llama.cpp · 14h ago · 3 views

llama.cpp v0.5.0 adds HRM-Text support, CUDA conv2d acceleration, and multi-address binding

The llama.cpp project has released version 0.5.0, focusing on backend performance, broader model coverage, and more robust server operation. This update introduces support for new architectures like HRM-Text (DFM Mimir 1B) and MiMo-V2.6, while significantly enhancing computational efficiency through CUDA and Metal optimizations.

github llama.cpp · 17h ago · 11 views

llama.cpp b11147 adds A8 Q6_K non-MoE dp4a OpenCL kernel

The llama.cpp project has released version b11147, which introduces a new binary kernel for OpenCL. This update specifically adds support for the A8 Q6_K non-MoE dp4a configuration.

github llama.cpp · 22h ago · 12 views

llama.cpp b11132 adds Gemma 4 DSpark draft backbone support

The llama.cpp project released version b11132, introducing support for the Gemma 4 DSpark draft backbone. This update enables GGUF conversion and runtime capabilities for full-attention and SWA Gemma 4 drafts, including tied output weights and boolean backbone metadata.

github llama.cpp · 1d ago · 13 views

llama.cpp b11122 extends MMVQ GLU fusion and adds new SYCL fusions

The llama.cpp project has released version b11122, which includes significant updates to the SYCL backend. The release extends the MMVQ GLU fusion to support mixed quantization types and introduces new fusions for rms_norm+scale and ssm_conv+silu operations.

github llama.cpp · 2d ago · 14 views

llama.cpp b11111 adds Intel Xe flash attention optimization kernels

The llama.cpp project released build b11111, which introduces Vulkan-based Intel Xe flash attention optimization kernels for split k paths on Xe-LPG Plus, Xe2, and Xe3 architectures.