All entries

Karpathy’s pattern: LLMs compile raw sources into a persistent interlinked markdown wiki—entity/concept pages, index, log—rather than re-deriving answers from RAG on every query.

We dive into these questions and other AI hot takes on the latest episode of the GitHub Podcast. The post Should you read the code, is RAG dead, and did Skills kill MCP? appeared first on The GitHub B

hexagon: matmul and flash-atten scalability updates (#29974) hexagon: head-parallel flash_attn partitioning for row-split multicore In row-split mode each core computes its output row shard of every M

We dive into these questions and other AI hot takes on the latest episode of the GitHub Podcast. The post Should you read the code, is RAG dead, and did Skills kill MCP? appeared first on The GitHub B

chat : add dedicated Ling 3.0 (Bailing V3) parser (#28682) chat: add dedicated Ling 3.0 (Bailing V3) parser Ling 3.0 Flash templates pre-open the think block in the generation prompt, so the model nev

In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework. The post AI-powered fuzzing with the GitHub Security Lab Taskflow Agent a

Describe the interface you need in plain English, then let the agent build a live surface you can both use and update—so you spend less time adapting to tools and more time getting work done. The post

cli: exit on stdin EOF and drop the console wide Ctrl+C broadcast (#29722) cli: exit on stdin EOF and drop the console wide Ctrl+C broadcast On Windows the simple input reader sends CTRL_C_EVENT to ev

Learn three ways to get noticed and grow your career as AI reshapes how developers build software. The post AI is rewriting the developer career ladder. Here’s how to stand out. appeared first on The

We’re launching ReviewBench, a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics. The post

The secondary button gets its own look back and the chat add button its own light surface. Pressable elements get a pointer cursor again, the font rendering smooths on the app shell, the root layout r

llama : check LoRA tensor data is within file bounds (#27056) llama : check LoRA tensor data is within file bounds Update src/llama-adapter.cpp Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggi

DeepseekV4: fix rollback with multi-seq (#26756) DeepseekV4: fix rollback with multi-seq fix model loading make pending rollback single use only clear cache for seq_id for full load add assert for com

Overview llama.cpp 0.4.0 adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml update to 0.23.0 with

gguf : align the data section relative to the GGUF start, not the file (#28993) gguf : align the data section relative to the GGUF start, not the file gguf_init_from_file_ptr reads a GGUF from the cur

Model-Saver: Write the SWA pattern, 15 more architectures roundtrip (#29042) llama: read the SWA pattern as a period or a per-layer array Add llama_model_base::load_swa_pattern(), which reads sliding_

Overview This release focuses on backend performance and correctness, broader model coverage, and more robust server/router operation. It adds HRM-Text (DFM Mimir 1B) support, MiMo-V2.6 and HunyuanOCR

Overview llama.cpp v0.6.0 introduces the new llama_batch_ext extended batch API (with llama_process) for mixed token/embedding inputs and MTP/deepstack state embeddings, adds support for the GLM-5.3-F

graph : reorder get_rows for embeddings (#30160) graph : reorder get_rows for embeddings cont : fix gemma4 and improve input embedding construction logic cont : add TODO for lora cont : fix raw embedd

Muse Glimmer Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other plat

Overview llama.cpp 0.3.0 introduces the dots3-note multimodal model (with a new DSA-ISWA KV cache), MTP support for GLM-4.5-Air, and tensor-split (-sm tensor) plus multi-sequence rollback fixes for De

model: add Qwen3.8-Flash-Next (qwen4exp) (#27742) gguf: add qwen4exp (Qwen3.8-Flash-Next) arch and converter Adds the GGUF-side plumbing for HF model_type qwen4_exp: MODEL_ARCH.QWEN4EXP plus tensors f

Overview llama.cpp 0.4.0 adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml update to 0.23.0 with

Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0.

server : allow RANK pooling batch splitting for causal LLM rerankers (ie. Qwen3 and Qwen3-VL) (#28876) server : allow splitting RANK pooling for causal LLM rerankers Rerank models fall into two catego

server : support typed content (vision/audio/video) input for /v1/embeddings endpoint (#29556) server : support multimodal input for /v1/embeddings (Qwen3-VL-Embedding) Accept the OpenAI-style wrapped

Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer bidirectional text encoder with PLE, shared gemma4 vision/audio towers, mean-pool + L2 output. /api/embed accepts per-item

Copilot now bills usage at listed API rates. Compare direct model access with the coding workflow, policy, and harness work around it. The post Copilot vs. raw API access: What are you actually paying

Fix Vulkan-Hpp handle usage on 32-bit targets. (#22892) On 32-bit platforms, Vulkan non-dispatchable handles such as VkBuffer are represented as uint64_t, and Vulkan-Hpp disables implicit conversions

metal : single-source fusion table + fusion debug rework (#28164) metal : rework fusion patterns into a single table All fusable op patterns for the Metal backend are now declared once in a fusion tab

OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv

batch: migrate the rest of examples to llama_batch_ext (#29601) migrate the rest test-thread-safety rm common_batch_staged Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cp

hexagon: matmul and flash-atten scalability updates (#29974) hexagon: head-parallel flash_attn partitioning for row-split multicore In row-split mode each core computes its output row shard of every M

ggml-openvino: skip unselected graph branches and support DUP Upstream #29622 adds a mixed token/embd branch to every input embedding graph through ggml_build_forward_select(). Its nodes are not flagg