Skip to content

Infrastructure 934 stories

llama.cpp releases Infrastructure

b10229

opencl: bugfix increment ref_count in ggml_backend_opencl_init() (#26162) Incrementing ref_count at the beginning is important later in the free() method of the ggml_backend_opencl_context at program end. If…

llama.cpp releases Infrastructure

b10228

DeepseekV4 MTP + DSpark (#25784) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…

llama.cpp releases Infrastructure

b10227

chat : add qwen3 specialized parser (#26252) Add tagged thinking tool parser chat : refactor and add permute helper cont : add support for omission cont…

llama.cpp releases Infrastructure

b10225

model : load MiMo V2 MTP tensors only if used (#26412) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…

llama.cpp releases Infrastructure

b10226

sycl: fix classification of iGPUs (#26105) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…

llama.cpp releases Infrastructure

b10224

ggml-webgpu: add support for f16 repeat (#26307) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…

llama.cpp releases Infrastructure

b10223

test: fix some CI errors (#26415) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…

llama.cpp releases Infrastructure

b10221

vendor : update BoringSSL to 0.20260730.0 (#26353) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…

llama.cpp releases Infrastructure

b10219

cli : persist reasoning_content in chat history (#26362) cli : persist reasoning_content in chat history llama-cli collected reasoning from the stream for display but only stored…

llama.cpp releases Infrastructure

b10218

mtmd: add minicpmv46 downsample (#25993) add minicpmv46 downsample Signed-off-by: tc-mb tianchi_cai@icloud.com put downsample mode inside gguf. Signed-off-by: tc-mb tianchi_cai@icloud.com build mtmd_image_preprocessor_llava_uhd Signed-off-by: tc-mb tianchi_cai@icloud.com fix code…

llama.cpp releases Infrastructure

b10217

chat : enable tool call in thinking for DS4 (#26269)

Together AI blog Infrastructure

Kimi K3: The Complete Developer Guide

Kimi K3 is the first open 3T-class model. See how it benchmarks, what it costs, and how to call it on the Together AI API, with…

NVIDIA Developer Infrastructure

Co-Designing AI Model Attention for Fast, Interactive Long-Context Inference

As agentic and long-context workloads become common, the context lengths increase and attention consumes a larger share of inference time (Figure 1). Because...

llama.cpp releases Infrastructure

b10216

vulkan: add POOL_1D op (#25431) vulkan : add pool1d push constants and pipeline field Declared data structures needed for POOL1D OP, which are the vk_op_pool1d_push_constants struct…

llama.cpp releases Infrastructure

b10215

vulkan: Introduce driver version check for Windows Intel GPU to mitigate crashing (#25192) Removed crash guard for Intel Crash fixed from driver 32.0.101.8860 Added driver version…

GitHub Copilot changelog Infrastructure

Upcoming August 2026 model deprecations in GitHub Copilot

We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions), on September 1st,…

llama.cpp releases Infrastructure

b10214

mtmd: add n_embd_head (#26342) Co-authored-by: Daniel Han unslothai@gmail.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…

llama.cpp releases Infrastructure

b10213

Support rotated kv cache quant (#26180) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…

GitHub Copilot changelog Infrastructure

Gemini 2.5 Pro and Gemini 3 Flash deprecated

As of today, July 31, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes,…

llama.cpp releases Infrastructure

b10212

llama : load MTP tensors only if they are really used (#26296) llama : load MTP tensors only if they are really used llama : skip…

llama.cpp releases Infrastructure

b10211

vulkan: update vulkan sdk to 1.4.357.0 (#26303) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…

GitHub Copilot changelog Infrastructure

Enterprise teams model policy targeting in public preview

![A configuration window for an enterprise team called Data team with the “Default models” tab selected, listing AI models and showing a status menu with “Enabled”…

llama.cpp releases Infrastructure

b10210

server: correct accepted tokens when need draft token replay (#26320) spec: correct accepted tokens when need draft token replay cont : naming Co-authored-by: Georgi Gerganov ggerganov@gmail.com…

llama.cpp releases Infrastructure

b10209

cuda: extract Q2_0 elements via __byte_perm (#25603) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…