Tencent Open-Sources AngelSpec: A Unified Training Framework for MTP and Block-Parallel Speculative Decoding on Hy3 Models
Source: MarkTechPost Tencent has released AngelSpec, an open-source, torch-native training framework for speculative-decoding draft models. The release covers...
Meet Token Saver: An Open-Source MCP Extension Using Local Hybrid RAG to Cut Claude PDF Token Costs 90-99%
Source: MarkTechPost AI developers, researchers, and professionals frequently hit a frustrating wall when analyzing large documents with LLMs:...
Moonshot AI Open-Sources MoonEP: A Perfectly Balanced Expert Parallelism Library for MoE Training
Source: MarkTechPost Moonshot AI has open-sourced MoonEP, an Expert Parallelism (EP) communication library for distributed Mixture-of-Experts (MoE) workloads....
Prompt Engineering vs Loop Engineering vs Graph Engineering: What Changes at Each Layer
Source: MarkTechPost Three terms now compete for the same line in AI engineering job descriptions. Prompt engineering is...
Liquid AI Releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M: Bidirectional Encoders That Stay Fast at 8K Context on CPU
Source: MarkTechPost Liquid AI has released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M. Both are masked language models...
Fireworks AI Releases Fireworks Nexus: A Drop-In Routing and Cost-Control Layer That Moves Routine Coding Work to Open-Weight Models
Source: MarkTechPost Fireworks AI has released Fireworks Nexus, an AI management and routing platform aimed at engineering organizations....
Microsoft AI Releases MAI-Cyber-1-Flash: A 5B-Active-Parameter Cyber Model That Pushes MDASH to 95.95% on CyberGym
Source: MarkTechPost Microsoft AI has released MAI-Cyber-1-Flash, its first model built specifically for cyber defense. The model does...
Deploying a 1-Bit Bonsai-27B Model with PrismML llama.cpp and OpenAI-Compatible Local Inference Workflows
Source: MarkTechPost In this tutorial, we deploy the 1-bit Bonsai-27B language model using the PrismML fork of llama.cpp,...
Kimi AI and kvcache-ai Open Sources ‘AgentENV’: A Distributed System that Powers Agentic Reinforcement Learning (RL) Training for Kimi K3
Source: MarkTechPost Moonshot AI’s Kimi team and kvcache-ai have open-sourced AgentENV (AENV), a distributed platform for running agent...
Perplexity Releases pplx, a Single-Binary CLI That Puts Its Search API in the Terminal for Coding Agents
Source: MarkTechPost Perplexity has released pplx, an official command line client for its Search API. The tool returns...