Models & Labs
llama.cpp adds MiniMax model support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances llama.cpp's capabilities with new model support.
- →Optimizes token sampling by addressing zero-valued embeddings.
- →Improves efficiency and robustness for developers using MiniMax models.
The b10437 release of llama.cpp brings support for the MiniMax-Text-01 and MiniMaxM1ForCausalLM models, focusing on optimizing the MiniMax-Text-01 model. Key improvements include the removal of state transpose operations and the introduction of a logits mask to manage zero-valued embeddings, which enhances the token sampling process. These updates aim to improve the efficiency and robustness of llama.cpp for developers using these models. The release does not introduce new model architectures but refines existing functionalities.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1llama.cpp adds MiniCPM5 tokenizer support
llama.cpp Releases · May 27, 2026 · Same story
- 2llama.cpp adds support for Gemma4ForCausalLM
llama.cpp Releases · May 27, 2026 · Same story
Follow this story
Open the full story →Kimi-K3 Text Model Added to llama.cpp
3 developments
- Aug 16 · llama.cpp Releases
Kimi-K3 Text Model Added to llama.cpp - Aug 16 · llama.cpp Releases
llama.cpp adds MiniMax model support (This article)↳ llama.cpp integrates MiniMax-Text-01 and MiniMaxM1ForCausalLM models with optimized token sampling via logits masks. - Aug 26 · llama.cpp Releases
llama.cpp v0.3.0 Release
More from llama.cpp Releases
Coding Toolscoding
llama.cpp fixes MoE dispatch inefficiency on Vulkan
This release targets a specific but costly bottleneck in Mixture-of-Experts inference on GPUs. The previous tile selection logic wasted significant compute time by misjudging the active workload per expert during dispatch. By correcting how matmul tiles are assigned, the patch ensures workers stay busy instead of idling. This is a quiet optimization that directly improves throughput for large MoE models running on Vulkan backends.
llama.cpp Releases
Coding Toolscoding
llama.cpp Vulkan perf boost on Intel Arc
Intel's discrete GPUs have long been second-class citizens in local inference due to inefficient memory access patterns. This patch fixes that by batching F32 matrix loads two at a time, squeezing significant throughput out of the B60 architecture. Benchmarks show raw GFLOPS jumping from 153 to 221 on specific shapes, proving that driver-level optimizations matter as much as model architecture. It’s a quiet but necessary fix for anyone running llama.cpp on AMD or Intel hardware.
llama.cpp Releases
Coding Toolscoding
llama.cpp b11267 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing first-class ROCm 10.0 support to both Linux and Windows. AMD GPU users no longer need workarounds for modern hardware, effectively closing a long-standing parity gap with NVIDIA's CUDA ecosystem. Equally notable is the new Snapdragon build for Linux, which targets the emerging AI PC market by leveraging Adreno GPUs and Hexagon NPUs directly. While KleidiAI on Apple Silicon has been disabled in this specific binary set, the expansion into non-NVIDIA silicon signals a strategic shift toward hardware agnosticism that benefits anyone running local models outside of standard data centers.
llama.cpp Releases
More in Models & Labs
© TechCrunch AIModels & Labsproductivity
OpenAI launches collaborative office suite features
OpenAI is directly challenging Microsoft’s dominance by embedding a full office suite into ChatGPT. The new 'Space' feature acts as a shared workspace where users and AI agents collaborate in real-time, while 'Pages' serves as an agent-native word processor. Collaborative slides allow teams to co-edit presentations generated from conversation. This marks a strategic pivot from pure chatbot utility to comprehensive workplace infrastructure, forcing incumbents to defend their core business models against an AI-native competitor.
TechCrunch AI
© Wes RothInvestment · $42 billion net loss
Models & Labsmodels
OpenAI delays GPT-6.1 Astra over safety risks
OpenAI has paused the release of GPT-6.1 Astra, citing significant safety concerns that outweigh its performance gains. This decision underscores a growing tension in the industry: as models become more capable, they also become harder to constrain within safe operational boundaries. While Anthropic pushes forward with Claude Sonnet 5.5 and reports massive financial losses ahead of an IPO, OpenAI is choosing caution over speed. The delay signals that safety evaluations are becoming a primary bottleneck for next-generation model releases, potentially shifting the competitive landscape toward more conservative development cycles. By halting Astra, OpenAI acknowledges that raw capability alone no longer guarantees a viable product launch. This move forces competitors to reconsider their own release timelines and safety protocols. The industry now watches closely to see if this caution becomes the new standard for frontier AI development.
Wes Roth
© TechCrunch AIModels & Labsproductivity
OpenAI expands ChatGPT plugins with app-like interfaces
OpenAI is shifting ChatGPT from a chat interface to an application platform by introducing dedicated sidebar panels and interactive tools for third-party developers. This move transforms static integrations into persistent, app-like experiences where users can view files and manage data without leaving the conversation. By supporting the MCP Events specification, OpenAI enables plugins to trigger automations based on external events, bridging the gap between conversational AI and workflow execution. The redesign of the plugin directory and creator tools aims to lower barriers for developers while giving users finer control over permissions. This effectively positions ChatGPT as a central hub for enterprise productivity rather than just a search or writing assistant.
TechCrunch AI