github llama.cpp · 2h ago · inference

llama.cpp b10275 decodes Windows OEM output to UTF-8 in built-in tools

from English

The llama.cpp project released build b10275, which fixes a character encoding issue on Windows where accented characters were silently lost. The update ensures that text from child processes writing in the OEM code page is correctly decoded to UTF-8 before reaching the JSON layer.

Resolves an issue where invalid bytes replaced accented output due to non-UTF-8 OEM code pages on Western Windows installs.
Uses MB_ERR_INVALID_CHARS to return text untouched instead of emitting replacement characters when a wrong code page is detected.
Prevents double-decoding by passing through text that already decodes as UTF-8.
Drops incomplete trailing sequences before validation to handle streamed chunks ending in the middle of multi-byte characters.

This fix preserves special characters in tool outputs, ensuring accurate data handling for users on Windows systems.

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

Read original

github llama.cpp · 5h ago

llama.cpp b10273 resolves sampler context length and removes full-context windows

The llama.cpp project released build b10273, addressing a critical issue where history-based samplers could not infer the correct context length during initialization due to backend-sampling constraints.

github llama.cpp · 7h ago

llama.cpp b10269 fixes dflash wo_a reshape on load

The llama.cpp project has released build b10269, which includes a fix for the dflash wo_a reshape issue during model loading.

media Hugging Face Forums · 10h ago

Open-source Decay-Gated O(N) Causal Linear Attention with fused Triton kernel

A developer has open-sourced a Decay-Gated O(N) Causal Linear Attention architecture featuring fused Triton/CUDA state accumulation kernels designed to bypass quadratic MHA bottlenecks.

github llama.cpp · 11h ago · 1 view

llama.cpp b10262 adds GATED_LINEAR_ATTN to Vulkan backend

The llama.cpp project released build b10262, which introduces support for the GATED_LINEAR_ATTN operation in its Vulkan backend. This update also includes documentation updates for Vulkan operations and removes an unused GLA spec constant.

github llama.cpp · 13h ago

llama.cpp b10259 allows tensor reshape during load

The llama.cpp project has released build b10259, which introduces the ability to allow the reshape of tensors during the loading process.