Topic: load
19 stories found
Tuesday, September 22, 2026
ggml/llama.cpp releases: b11114
The ggml/llama.cpp server was updated to fix router eviction race conditions by routing all model loads through a queue, ensuring that no model is evicted prematurely during loading. This update is crucial for improving the stability and reliability of model handling in the server.
Monday, September 21, 2026
macOS 27: Workaround to avoid downloading AI models and save storage
Apple released an update for macOS that includes a workaround to prevent the automatic download of AI models, helping users conserve storage space. This update is significant as it addresses user concerns about storage usage by AI features without compromising functionality.
ggml/llama.cpp releases: b11090
The ggml/llama.cpp project fixed a compilation error related to CUDA sm_70 tiles by generalizing the tile shape in version b11090, addressing an issue where a recent update mismatched tile definitions. This update is crucial for ensuring compatibility across different GPU architectures.
Sunday, September 20, 2026
ggml/llama.cpp releases: b11062
The ggml/llama.cpp project released version b11062, which includes a CUDA update enabling sparse FA for qwen4 (#28770). This update is significant as it enhances the performance and efficiency of the model on specific hardware.
Saturday, September 19, 2026
ggml/llama.cpp releases: b11056
The ggml/llama.cpp project released version b11056, which includes a change to enable I32 GET_ROWS (#29116). This update is significant for improving the handling of 32-bit integer operations in the library, potentially enhancing performance and functionality.
OpenClaw Releases 2026.9.5 With Atomic Updates, Plugin Hot Reload, Conversation Sharing, and Expanded GPT Live
OpenClaw 2026.9.5 introduces significant updates including Atomic Updates and plugin hot reload, enhancing stability and development flexibility. These changes, along with features like read-only conversation sharing, are part of a major 4,179 pull request update from 502 contributors, marking a substantial improvement in the platform's functionality and usability.
Friday, September 18, 2026

ZCode, the GLM coding agent, silently uploads your Git history
ZCode, a GLM coding agent, was found to silently upload users' entire Git history without consent, raising serious privacy concerns. This incident highlights the potential risks of using third-party tools for software development and underscores the need for enhanced security measures and user awareness.
ggml/llama.cpp releases: b11045
The ggml/llama.cpp project released version b11045, which includes support for the ROLL operation. This update is significant as it enhances the project's capabilities, particularly in handling specific types of data transformations.

The Download: AI’s extinction risk and bioweapons threat
MIT Technology Review hosted a roundtable discussion questioning whether AI poses an extinction risk and bioweapons threat, addressing concerns that AI could potentially harm humanity. The event aimed to explore these fears and provide answers based on expert insights.
Thursday, September 17, 2026
ggml/llama.cpp releases: b11028
The ggml/llama.cpp project released version b11028, which includes a fix for evicting old files. This update is important as it enhances the project's stability and efficiency, particularly for users on Apple Silicon platforms.
19 of 19 items shown. Sources: 124 days indexed.