AI and infrastructure news | Wendelmaques

Skip to content

Project140

Speech: TTS and ASR Project
10/08/2618 days ago github.com
Ultravox and real-time voice applications
The GitHub repository presents Ultravox as a fast multimodal LLM for real-time voice. Published on November 18, 2024, the project makes its source code available for examination.
Reinforcement learning Project
10/07/2619 days ago github.com
RL environments and training code for language models
On September 26, 2026, Xiaomi MiMo published reinforcement learning environments, training code, and a dataset for experiments with language models.
Reinforcement learning Project
10/07/2619 days ago github.com
SQL-based replay buffer sampling
A post published on August 16, 2026 describes weighted top-k sampling in SQL and reports selecting 8,192 rows from 50 million in about 1.1 seconds on a laptop.
Attention and model architecture Project
10/07/2619 days ago github.com
Continual learning in LLMs with iSDFT
A repository published on September 22, 2026 presents a self-distillation method for continual learning in LLMs, with training code, checkpoints, and evaluations.
Attention and model architecture Project
10/07/2619 days ago github.com
Continuous learning on a notebook with 8 GB of VRAM
The mini-AGI repository describes a model trained from scratch on a notebook with 8 GB of VRAM, using batch size 1, disk-paged weights, and learning-rate adjustments to reduce forgetting.
Speech: TTS and ASR Project
10/07/2619 days ago github.com
Breeze TTS 2 opens model weights
On August 26, 2026, BreezeBlue announced open weights for Breeze TTS 2 and said the model leads a voice evaluation arena.
AI agents Project
10/07/2619 days ago github.com
Buzz publishes a specification for agent memory
On July 28, 2026, Buzz published the NIP-AE specification for its memory feature, aiming to support implementation and interoperability.
OCR and document AI Project
10/07/2619 days ago github.com
Tax-page classifier evaluated on 261 forms
A GitHub repository describes an open-source classifier for tax-document pages and reports 100% strict accuracy on 261 IRS forms, at about US$0.001 per page.
Speech: TTS and ASR Project
10/07/2619 days ago github.com
CocktailASR-1 transcribes a selected voice in overlapping audio
Published by Xiaomi on September 16, 2026, CocktailASR-1 uses reference voiceprints to transcribe a chosen speaker in mixed audio. The publication reports support for English and Chinese.
LLM inference Project
10/07/2619 days ago github.com
Colibri streams MoE experts from disk for local inference
A pure-C inference engine loads experts from mixture-of-experts models from disk, offering an approach to evaluate local execution on hardware with limited memory.
OCR and document AI Project
10/07/2619 days ago github.com
How to structure OCR testing for your business
In a post published on July 25, 2026, the author says Baidu Unlimited OCR was added to mlx-vlm and plans to evaluate it using an OCR benchmark.
LLM inference Project
10/07/2619 days ago github.com
Reproducing multi-GPU serving and thermal profiling
A GitHub repository published on July 30, 2026 presents a reproducible GLM-5.2 EXL3 MTP3 serving configuration and thermal profile for four RTX PRO 6000 Blackwell GPUs.
LLM inference Project
10/07/2619 days ago github.com
Model communication on Huawei Ascend NPUs
The publication, dated September 30, 2026, describes a high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.
LLM inference Project
10/07/2619 days ago github.com
Inference configuration across two DGX Sparks
A pull request dated July 31, 2026 updates the default checkpoint and installs the encoder on both ranks in a two-DGX-Spark configuration.
Training and fine-tuning Project
10/07/2619 days ago github.com
datatrove 0.10.0 runs pipelines on managed jobs
datatrove 0.10.0 adds pipeline execution on managed jobs, support for storage buckets as data folders, and preservation of reasoning outputs in inference results.
C and C++Project
10/07/2619 days ago github.com
Software debugging: a methodology beyond Unix and Python
The open book The Art of Debugging is available in PDF and EPUB, has five chapters, and covers Unix, Python, and PyTorch. Its author says the methodology chapter applies to software debugging in general.
Attention and model architecture Project
10/07/2619 days ago github.com
Recurrent state could extend Transformer memory
The description of the Recurrent Looped Transformer, dated September 13, 2026, presents a recurrent decoder that preserves state between tokens to extend the temporal information path.
LLM inference Project
10/07/2619 days ago github.com
Silent failures in LLM serving: a practical diagnosis
Published on July 28, 2026, the GitHub repository catalogs LLM serving failures, their symptoms, mechanisms, checks, and fixes.
Speech: TTS and ASR Project
10/07/2619 days ago github.com
FireRedAudio combines five speech tasks in one model
Published on August 27, 2026, FireRedAudio combines speech recognition and understanding, speech generation, and speech editing, using distinct representations for audio comprehension and generation.
Reinforcement learning Project
10/07/2619 days ago github.com
FrontierSmith publishes 200 open-ended RL problems
On September 28, 2026, FrontierSmith published a repository of 200 problems for studying reinforcement learning on challenging, open-ended tasks.
Training and fine-tuning Project
10/07/2619 days ago github.com
GuppyLM: an experiment with a 9-million-parameter model
In a post published on September 19, 2026, the author describes GuppyLM, a model with about 9 million parameters that, according to the author, can be trained from scratch in five minutes.
AI agents Project
10/07/2619 days ago github.com
Harness expands browser and computer options for agents
Version v0.1.6-alpha.1, published on September 15, 2026, adds persistent terminals, multiple tabs, MCP support, and experimental options for browser and computer use.
Training and fine-tuning Project
10/07/2619 days ago github.com
IFM-AI releases open tools for LLMs
On September 28, 2026, IFM-AI announced open-source tools for LLM pre-training, attention, checkpoint conversion, and serving.
LLM inference Project
10/07/2619 days ago github.com
LLM inference with limited VRAM
A post dated July 17, 2026 describes a framework for heterogeneous inference and fine-tuning, distributing experts across GPU and CPU.
Training and fine-tuning Project
10/07/2619 days ago github.com
KohakuFA proposes an alternative for backward-pass precision
On October 3, 2026, a post presents the KohakuFA kernel as an alternative amid claims of precision issues in backward passes involving cuDNN, FA4, and FlexAttention.
Training and fine-tuning Project
10/07/2619 days ago github.com
Kyutai opens the Pocket TTS training stack
On August 25, 2026, Kyutai published the Pocket TTS training stack, including a data pipeline, training recipes, and evaluations for a text-to-speech model designed to run on CPU.
LLM inference Project
10/07/2619 days ago github.com
Open book covers 12 chapters on AI infrastructure
Published on September 13, 2026, the book covers model architectures, accelerators, inference, and training. Its scope can help companies identify concrete infrastructure challenges.
Training and fine-tuning Project
10/07/2619 days ago github.com
MaAI expands training data for its English VAP model
In a post published on September 6, 2026, MaAI says its English VAP model was trained with a larger scale of data. The project describes real-time prediction of conversational cues and head movements.
C and C++Project
10/07/2619 days ago github.com
Movfuscator limits C code to the MOV instruction
Published on August 17, 2026, the repository presents a C compiler that generates Turing-complete assembly using only MOV, a useful case for evaluating code analysis tools.
AI agents Project
10/07/2619 days ago github.com
Code notebooks explore agent design patterns
Published on August 25, 2026, Antonio Gulli’s guide presents notebooks for exploring patterns including prompt chaining, routing, reflection, tool use, planning, and multi-agent systems.
Security Project
10/07/2619 days ago github.com
Compile-time C obfuscation on Windows
The obfus.h repository describes a macro header for compile-time C obfuscation on Windows x86/x64 with tcc, including virtualization, anti-debugging, and control-flow obfuscation.
OCR and document AI Project
10/07/2619 days ago github.com
OCR for long documents in a single pass
A post published on June 23, 2026 describes an OCR model that processes documents longer than 40 pages in one pass while keeping KV Cache size constant.
OCR and document AI Project
10/07/2619 days ago github.com
Local iPhone OCR with API access on the network
A post published on August 26, 2026 describes iOS-OCR-Server, an open-source project that uses Apple's Vision framework to process OCR locally on an iPhone and expose an API to devices on the same network.
AI agents Project
10/07/2619 days ago github.com
Octop combines multi-user agents with self-hosting
A Tencent Cloud post published on September 15, 2026, presents Octop, an open-source, self-hosted AI assistant platform with local data storage and team integrations.
Speech: TTS and ASR Project
10/07/2619 days ago github.com
OmniVoice: speech synthesis and voice cloning in 600+ languages
A publication dated September 6, 2026 describes a Python speech-synthesis project with zero-shot voice cloning, support for more than 600 languages, and configurable voice controls.
Attention and model architecture Project
10/07/2619 days ago github.com
OpenMythos explores a recurrent-depth Transformer
Published on June 19, 2026, the repository presents an open-source theoretical reconstruction featuring recurrent depth, MoE routing, and adaptive halting per token.
AI agents Project
10/07/2619 days ago github.com
OpenShell proposes a secure runtime for autonomous agents
Published on September 28, 2026, the GitHub repository describes OpenShell as a runtime focused on the security and privacy of autonomous AI agents.
OCR and document AI Project
10/07/2619 days ago github.com
PaddleOCR 3.7 expands inference options for OCR
In a post published on June 17, 2026, PaddleOCR announced an ONNX Runtime inference backend and CPU inference via OpenVINO, as well as GPU inference via CUDA and TensorRT. The post says PP-OCRv6 models can be up to 3.9 times faster on CPU.
Speech: TTS and ASR Project
10/07/2619 days ago github.com
ComfyUI plugin supports local voice and LoRA tuning
Published on August 25, 2026, the ComfyUI_VoxCPM_SM repository presents VoxCPM2 inference and LoRA fine-tuning with custom voice data, supporting low VRAM and quantized models.
Security Project
10/07/2619 days ago github.com
Post announces bootrom exploit for Apple chips
Published on June 18, 2026, the post says a bootrom exploit was released for A12, A13, S4/S5, and A12X/Z chips, which have not yet been tested.

Let's assess your project

Wendelmaques Pereira

I reply with scope and a proposal.

Looking for something else?Frequently asked questions Guides Contact