github llama.cpp · 2h ago · inference

llama.cpp b10598 uses pillow-accurate resize algo and corrects resize_algo for all models

from English

The llama.cpp project released build b10598, which updates the mtmd module to use a pillow-accurate resize algorithm and corrects the resize_algo for all models. This release also includes speed optimizations.

The mtmd module now employs a pillow-accurate resize algorithm.
The resize_algo has been corrected across all models.
General speed optimizations were applied.

This update ensures more accurate image resizing in the mtmd module and improves performance for users running llama.cpp on macOS, iOS, Linux, Windows, Android, and openEuler.

Importance 1/3 Trust 1/3 llama.cpp Inference efficiency Local inference

Read original

github llama.cpp · 8h ago · 3 views

llama.cpp b10593 fixes DeepseekV4 rollback and model loading

The llama.cpp project has released build b10593, which addresses critical issues with the DeepseekV4 model architecture. The update specifically resolves a rollback failure that occurred during multi-sequence processing.

github llama.cpp · 1d ago · 2 views

llama.cpp b10584 fixes draft context sizing to prevent server 500 errors

The llama.cpp project released build b10584, addressing a critical issue where the draft context size did not match the target context, causing server requests to fail with 500 errors.

github llama.cpp · 2d ago · 5 views

llama.cpp b10568 uses ggml_rope_set_offset() for DeepSeek 2

The llama.cpp project released build b10568, which updates the model handling to use the `ggml_rope_set_offset()` function. This change is partially applied to support DeepSeek 2.

media Hugging Face Forums · 2d ago · 4 views

Celestium Engine adds VRAM optimizations and CPU fallback for SDXL

The Celestium Engine has introduced several upgrades to improve SDXL performance on low-VRAM hardware. These changes focus on memory management, stability, and fallback mechanisms to ensure consistent generation even on constrained systems.

github llama.cpp · 3d ago · 9 views

llama.cpp b10541 adds --mmproj-device argument for multimodal projects

The llama.cpp project released build b10541, introducing the `--mmproj-device` command-line argument to allow users to specify the device backend for loading multimodal projection files.