github llama.cpp · 1h ago · inference

llama.cpp b10219 persists reasoning_content in chat history

from English

The llama.cpp project released version b10219, which includes a fix for the CLI to persist reasoning content within the chat history. Previously, while `llama-cli` collected reasoning from the stream for display, it only stored assistant content in messages, preventing the `--reasoning-preserve` flag from re-injecting prior thoughts on later turns.

This update ensures that reasoning steps are now correctly retained in the message history, allowing multi-turn conversations to maintain context of the model's internal thought process. The release provides binaries for macOS (Apple Silicon and Intel), iOS, Linux (CPU, Vulkan, ROCm, OpenVINO, SYCL), Android, Windows (CPU, CUDA 12/13, Vulkan, OpenCL, OpenVINO, SYCL, HIP), and openEuler.

By fixing this persistence issue, users can now effectively use the `--reasoning-preserve` option to carry forward reasoning context across multiple turns in CLI interactions.

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

Read original

github llama.cpp · 22h ago · 3 views

llama.cpp b10213 adds support for rotated kv cache quantization

The llama.cpp project has released version b10213, introducing support for rotated key-value cache quantization. This update is available across a wide range of platforms and hardware accelerators.

github llama.cpp · 23h ago · 1 view

llama.cpp b10212 loads MTP tensors only when used

The llama.cpp project released version b10212, which includes a change to load Multi-Token Prediction (MTP) tensors only if they are actually used. This update ensures that MTP tensors are skipped during loading for remaining models that support the feature but do not require it.

github llama.cpp · 1d ago

llama.cpp b10210 corrects accepted tokens during draft token replay

The llama.cpp project has released version b10210, which includes a correction to the server logic for handling accepted tokens when draft token replay is required.

github llama.cpp · 1d ago

llama.cpp b10208 adds oneMKL GEMM flash attention for XMX-accelerated prompt processing

The llama.cpp b10208 release introduces SYCL support for oneMKL GEMM flash attention, enabling XMX hardware acceleration for prompt processing. This change significantly improves inference speed on Intel Arc GPUs by utilizing MKL kernels instead of the default TILE path.

github llama.cpp · 1d ago

llama.cpp b10207 adds SYCL support for missed types in cpy

The llama.cpp project has released version b10207, which includes a pull request to add SYCL support for previously unsupported data types in the cpy operation.