Tới nội dung

Lĩnh vực

Mã nguồn mở Mới nhất

Mô hình trọng số mở tải về tự triển khai được, các framework mã nguồn mở và dự án AI đang nổi trên GitHub.

43 tin chọn30 trong 30 ngày quaĐã thu thập 186

Cập nhật 13 tháng 11 08:32

Mã nguồn mở

Hôm nay13 tháng 11Thứ SáuMục 1–20 trong 43
  1. Hacker News · AI76

    Phát hành mã nguồn mở AgentRun: Bổ sung khả năng tự cải thiện và thực thi bền vững cho các agent harness hiện có

    Parcha Labs đã mã nguồn mở AgentRun, một nền tảng agent bổ sung lớp tự cải thiện, thực thi bền vững và một console lên trên Claude Code, Codex, OpenCode và pi, theo giấy phép Apache-2.0.

    Vì sao đáng chú ý: AgentRun bổ sung lớp tự cải thiện, thực thi bền vững và một console lên trên các harness hiện có như Claude Code và Codex, đồng thời cung cấp một trường hợp cụ thể trong đó chi phí đánh giá mã giảm từ 6.451 đô la mỗi tháng xuống còn 18 xu mỗi lần chạy.

  2. Hacker News · AI88

    Edge0 mã nguồn mở các mô hình trên thiết bị Edge0-145B và Edge0-120B cùng khung suy luận

    Edge0 đã mã nguồn mở Edge0-145B và Edge0-120B cùng khung suy luận thống nhất và các công cụ triển khai, tuyên bố Edge0-145B là mô hình trên thiết bị 145 tỷ tham số mã nguồn mở đầu tiên. Công ty báo cáo bộ nhớ đỉnh 29GB, prefill 1.100+ token/giây, decode 80+ token/giây và công suất tiêu thụ điển hình khoảng 120W trên một laptop tương thích, với ngữ cảnh 128K–256K. Họ dẫn điểm số nội bộ 64,6 trên DeepSWE 1.1, 86,52 trên Terminal-Bench 2.1, 90,4 trên GPQA-Diamond và 80,6 trên IFBench, và cho biết trọng số có trên Hugging Face với hỗ trợ ngay từ ngày đầu cho macOS, Windows và Linux.

    Vì sao đáng chú ý: Edge0 mã nguồn mở một mô hình trên thiết bị 145B báo cáo bộ nhớ đỉnh 29GB và decode 80+ token/giây, mang lại một dữ liệu cụ thể về mức độ mà suy luận cục bộ có thể mở rộng.

  3. Hugging Face Blog69

    IBM phát hành các mô hình xem trước LLMON được xây dựng trên Granite 4.1 3B và 8B

    IBM đã phát hành hai mô hình xem trước thử nghiệm, granite-4.1-3b-LLMON-preview và granite-4.1-8b-LLMON-preview, được phát triển từ các checkpoint cơ sở Granite 4.1 và được huấn luyện để tiếp nhận và tạo ra LLMON, một ngôn ngữ đánh dấu bản địa của LLM đánh dấu chỉ dẫn, dữ liệu và yêu cầu bằng các dấu phân cách token đặc biệt dành riêng. Trên bộ đánh giá OPI, các mô hình tránh được nhiều hơn 47% các cuộc tấn công chèn prompt gián tiếp so với mô hình tiên tiến nhất được thử nghiệm và nhiều hơn 95% so với mô hình mã nguồn mở tốt nhất, đồng thời hoạt động ngang bằng với Granite 4.1 Instruct trên các bộ đánh giá tiêu chuẩn. Bản phát hành bao gồm một bộ công cụ GitHub với các bộ chuyển đổi JSON sang LLMON không mất dữ liệu, và các tác giả lưu ý rằng bản xem trước dành cho mục đích khám phá, không phải để sử dụng trong môi trường sản xuất.

    Vì sao đáng chú ý: IBM đã huấn luyện một mô hình xem trước trên Granite 4.1 có thể đọc và ghi các thẻ LLMON, sử dụng việc tách biệt rõ ràng giữa chỉ dẫn và dữ liệu để giảm tỷ lệ thành công của các cuộc tấn công chèn prompt gián tiếp trên bộ đánh giá OPI xuống gần bằng không trong khi vẫn duy trì các khả năng chung.

  4. AWS Machine Learning Blog66

    AWS updates AgentCore runtime with 15x faster session starts and 4x more compute

    AWS announced updates to Amazon Bedrock AgentCore runtime, its managed compute layer for agents, with sessions now starting up to 15x faster, scaling to 4x more compute (up to 8 vCPUs and 32 GB, with container images up to 10 GB) and running up to 68% more efficiently, while each session stays in its own hardware-isolated Firecracker MicroVM. Sessions start in under 2 seconds regardless of image size or concurrency, idle agents scale to zero, and agents can mount and save work to a filesystem such as an Amazon S3 bucket with FUSE support so data stays inside the trust boundary. The runtime is available today in AWS Regions across North America, South America, Europe, and Asia Pacific.

    Vì sao đáng chú ý: AgentCore runtime 的新版本把会话启动、算力上限和内存计费一起调整，为需要长时间运行的智能体提供了隔离与成本之间的新取舍。

  5. AWS Machine Learning Blog60

    AWS open-sources UAEF, a framework-agnostic evaluation system for AI agents

    AWS has open-sourced UAEF (Universal Agent Evaluation Framework), a framework-agnostic system that uses adapters to normalize agent traces from LangGraph, LangChain, Strands Agents, Amazon Bedrock AgentCore and Langfuse into one canonical AgentTrace, then scores them with 36 built-in metrics across 7 dimensions. Results are stored per experiment in Amazon DynamoDB and Amazon S3, so teams can compare agent versions against a baseline, flag regressions with a default 5 percent threshold, and generate statistical reports plus LLM-written insights. The post says customers across 12 organizations in telecom, healthcare and financial services used UAEF before release, and the Apache 2.0 code, Python library, CDK deployment and per-framework notebooks are in the awslabs/uaef GitHub repository.

    Vì sao đáng chú ý: The AWS team has open-sourced UAEF, which uses adapters to unify agent trajectories from different frameworks into a single format, then scores them across 7 dimensions using 36 metrics, providing a reusable evaluation layer for comparing agent versions across frameworks.

12 tháng 11Thứ Năm
  1. vLLM Blog60

    vLLM adds day-0 support for Thinking Machines' Inkling 2 Small

    vLLM supports Thinking Machines' Inkling 2 Small on day 0, a multimodal text-and-vision MoE with 594B total and 17B active parameters and up to 1M tokens of context. The integration adds kernel fusion with PDL, sequence parallelism for prefill that cuts an 8K-token prefill step by 22% at TP4 and 26% at TP8, and a Gluon relative attention decode kernel that drops a batch-1 decode step at 100K context from 15.1 ms to 4.8 ms. vLLM reports up to 630 TPS/user at TP4 on GB200 with acceptance length 3.5, and also supports LoRA and RL via SkyRL.

    Vì sao đáng chú ý: vLLM 在发布当天即支持 Inkling 2 Small，并给出内核融合、序列并行和 Gluon 解码内核的具体优化数据，可供部署大 MoE 模型的团队参考。

  2. vLLM Blog64

    vLLM-Omni benchmarks MiniMax H3-Image on Vera Rubin: 0.87s 4K generation and 6,115 images/hour

    vLLM-Omni brought MiniMax H3-Image to NVIDIA Vera Rubin and measured 0.87-second median latency for native 4096×4096 text-to-image on four GPUs, plus 6,115 images/hour in a separate throughput configuration. H3-Image is an open-weight text-to-image and editing model that pairs a Qwen3-VL encoder with a 33.1B dense DiT and an image VAE, handling both tasks in six sampling steps with up to 16 reference images. The team reports MXFP8 DiT GEMMs, Ulysses SP4, AdaLN caching and a VAE decoding change that cut decode time from 2.635s to 0.213s, and lists recipes for AMD, Intel, Huawei Ascend and Moore Threads hardware.

    Vì sao đáng chú ý: vLLM-Omni's benchmark shows MiniMax H3-Image running on Vera Rubin at subsecond 4K latency, with per-hardware configurations and a cost model for serving economics.

11 tháng 11Thứ Tư
  1. LangChain Blog60

    LangChain explains how Deep Agents manages context without keeping everything in the window

    LangChain details how its open source Deep Agents harness uses middleware to fight context rot on long agent runs. Tool results over roughly 20,000 tokens and user messages over 50,000 tokens are offloaded to files with only a preview shown, while summarization condenses older messages once usage hits 85% of the context window. Skills, subagents and a markdown long-term memory file keep the main agent's window small and let memory carry over across models and providers.

    Vì sao đáng chú ý: LangChain explains how its open source Deep Agents harness uses middleware to offload, summarize and isolate context, offering a reusable pattern for agents on long tasks.

  2. MiniMax Blog75

    MiniMax releases H3-Image, an open-weight model generating 4K images in under 10 seconds

    MiniMax released H3-Image, an open-weight image generation model built on H3 that supports text-to-image, reference-based generation and image editing, and can produce a 4096 × 4096 image in under 10 seconds. The company says it handles up to 16 reference images, claims state-of-the-art prompt adherence among open-weight models, and reports speeds up to 5× mainstream alternatives. H3-Image is available via the MiniMax API Platform, MiniMax Code and Hailuo AI, priced at 50–70% of comparable offerings, with 50% off 4K-and-above requests during launch week.

    Vì sao đáng chú ý: MiniMax releases open-weight H3-Image, claiming sub-10-second 4K generation and pricing at 50–70% of comparable mainstream offerings, giving developers a new open option for high-resolution image work.

  3. NVIDIA Blog60

    NVIDIA Contributes OpenShell Agent Runtime to CNCF and Adds DSX Kubernetes Tools

    NVIDIA is contributing OpenShell, its open source runtime for securing and governing autonomous agents, to the Cloud Native Computing Foundation as a Sandbox project, and is also contributing to Google-led Agent Substrate. NVIDIA announced three new DSX AI Factory Platform components: NVIDIA Kubernetes Engine and NVIDIA Kubernetes Recipes, now in public preview, and NVIDIA Snapshot, which restores checkpointed replicas in seconds without model reload or warmup. Crusoe tested GLM-5.3 on Crusoe Cloud and cut workload ready time from roughly eight minutes to 31 seconds, while Saturn Cloud reduced vLLM startup from between two and 8.5 minutes to six and 34 seconds.

    Vì sao đáng chú ý: NVIDIA contributes its agent security runtime OpenShell to CNCF and adds Kubernetes tooling for GPU AI factories, with early Snapshot results cutting inference startup from minutes to seconds.

  4. Google Developers Blog75

    Google releases A2UI 1.0, a stable open protocol for agent-generated native UI

    Google released A2UI 1.0, the first stable version of its open protocol that lets AI agents answer with interactive screens rendered by each app's own native components. Version 1.0 adds bidirectional function calls, accessibility support and extension metadata, plus open-source renderers for React, Angular, Lit, Flutter, SwiftUI and Jetpack Compose (the Compose renderer is at 0.9.1 with 1.0 coming soon) and agent SDKs for Python, TypeScript and Dart. Atlassian is bringing A2UI to Jira, Alation renders its feeds with it in Claude, and ByteDance shipped a Lynx renderer in June 2026 that supports 0.9 today.

    Vì sao đáng chú ý: Google's stable A2UI 1.0 protocol lets agents return native interactive screens instead of text walls, with renderers for web, Android and iOS and early adopters including Atlassian and ByteDance.

10 tháng 11Thứ Ba
  1. Amazon Science62

    Amazon releases Mitra-v2 tabular foundation model with scaled synthetic pretraining

    Amazon introduced Mitra-v2, a second-generation tabular foundation model for classification and regression, released with fine-tuned models and inference and fine-tuning code under the Apache-2.0 license on Hugging Face. It is pretrained on synthetic tables with 10 times as many rows and roughly three times as many columns as Mitra-v1, using a new hybrid SCM prior and hybrid optimizer while keeping the Transformer architecture unchanged. On TabArena, a public benchmark of 51 real-world datasets, Mitra-v2 leads the single-model field, beats Mitra-v1 on 32 of the 33 datasets both run natively, and finishes all 51 within the one-hour budget; fine-tuned Mitra-v2 also ranks first on ScoringBench.

    Vì sao đáng chú ý: Mitra-v2 shows that widening synthetic pretraining data, rather than deepening the network, lifts a tabular foundation model to the top of TabArena's single-model field.

  2. Goodfire Research62

    Goodfire studies Qwen3.6-35B-A3B neurons as an interpretable basis

    Goodfire Research published a study arguing that individual MLP neurons in Qwen3.6-35B-A3B are more interpretable than assumed, based on sparsification, attribution tools and research agents. Ablating the 92.2% weakest MoE neuron activations per forward pass raised language model loss by only 2.9%, and 69% of neuron poles had a single mode responsible for at least 90% of their causal effect. Natural-language neuron descriptions let a judge model predict firing with 95% accuracy against random text and recover 73% of ablation damage through simulation.

    Vì sao đáng chú ý: Goodfire's study of Qwen3.6-35B-A3B neurons argues that strong activations alone carry most of the model's computation, offering a concrete alternative to feature-dictionary interpretability.

  3. Google Developers Blog72

    Google AI Edge Gallery adds on-device speech recognition and text-to-speech

    Google introduced on-device Automatic Speech Recognition and Text-to-Speech in Google AI Edge Gallery, letting apps run multilingual ASR and expressive TTS fully offline alongside on-device SLMs like Gemini Nano and Gemma 4. On Android, ML Kit's new speech models transcribe 100+ languages at 10x real-time speed with an 8.0% to 9.0% Word Error Rate on FLEURS, while the few-step diffusion TTS starts speaking in about 100 ms and generates 24 kHz audio at up to 50x real-time speed. Cross-platform support comes through MediaPipe Tasks and LiteRT with open-weight bundles including Parakeet-TDT 0.6B, PocketTTS 100M, Kokoro-82M and Phonon 31M, demonstrated in the XR Language Teacher showcase and voice-enabled AI Chat.

    Vì sao đáng chú ý: Google adds fully offline ASR and TTS to AI Edge Gallery, with ML Kit reporting 100+ language transcription at 10x real time and a diffusion TTS that starts speaking in about 100 ms.

9 tháng 11Thứ Hai
  1. NVIDIA Blog70

    NVIDIA unveils GR00T 2 world action model and Isaac Lab 3.0 at CoRL

    NVIDIA introduced GR00T 2, an open world action model built on Cosmos and trained on 100,000 hours of human egocentric data, alongside Isaac Lab 3.0 and new robotics benchmarks at CoRL. GR00T 2 completed 40 of 50 evaluated tasks at least once without task-specific demonstrations and reached 71% average success across 50 tasks with one demonstration each, rising to 95% with five. Isaac Lab 3.0 adds Newton physics integration for deformable objects and reports up to 2.5x the training throughput of Isaac Lab 2.3 with PhysX in a vision-based dexterous manipulation benchmark.

    Vì sao đáng chú ý: NVIDIA's CoRL release shows how simulation plus world action models now target delicate assembly work, with GR00T 2 and Isaac Lab 3.0 details worth comparing against prior robotics stacks.

  2. Zyphra Research78

    Zyphra releases ZONOS3-Mini, an Apache 2.0 zero-shot voice-cloning TTS model that runs on-device

    Zyphra released ZONOS3-Mini, a sparse MoE text-to-speech model with 100M active and 800M total parameters under Apache 2.0, trained on 112 NVIDIA H100s in 2.5 days. It reaches under 570 ms time-to-first-audio in the browser on a Pixel 9 and under 150 ms on an M3 MacBook Air, with runtimes for WebGPU, SGLang, vLLM and GGML. The model adds control over identity, accent, quality, mood and delivery, including word-level steering, and Zyphra reports it ranks first among open models on its new ZTTS2-Eval benchmark.

    Vì sao đáng chú ý: Zyphra's compact MoE TTS model pairs zero-shot voice cloning with word-level delivery control while running in real time on phones and laptops.

  3. Google Developers Blog60

    Google Cloud MaxText adds context parallelism for long-context training on TPUs

    Google Cloud released long-context training support in MaxText v0.2.4, its open-source JAX training framework, adding four context-parallel strategies on Cloud TPU: All-gather, A2A (DeepSpeed Ulysses), P2P (Ring Attention) and the A2A + P2P hybrid (USP). Benchmarks with Llama 3.1 8B reached 70% MFU on TPU 5p at sequence lengths up to 4 million tokens, and context extended to 14 million tokens on both TPU 5p and TPU 7, with TPU 7 holding 50% MFU below 6 million tokens. The release is available on PyPI, in Docker images and on GitHub main, with sample recipes for TPU 7 and TPU 5p.

    Vì sao đáng chú ý: MaxText's four context-parallel strategies on Cloud TPU, with benchmark MFU figures for Llama 3.1 8B, give teams a concrete reference for choosing how to train at multi-million-token sequence lengths.

6 tháng 11Thứ Sáu
  1. vLLM Blog77

    REINFORCE Zero: Kernel Alignment Enables Stable Async RL at Policy Lag 64, Extends to DeepSeek-V4.1 and Kimi K3.1

    NVIDIA Research and Inferact's REINFORCE Zero paper shows that aligning rollout and trainer kernels lets unclipped token-level importance sampling correct the remaining weight lag, training stably for 20,000 updates at policy lag 64 and reaching 2.40x the training-step throughput of synchronous training with aligned kernels. With standard kernels, the median rollout-to-learner KL rises 83.33x across the run and online AIME24 pass@1 falls from 34.27% to 13.96%, while a sequence gate stabilizes training but rejects 24.48% of sequences by the last 1,000 updates. The zero-mismatch setup now covers DeepSeek-V4.1-Flash, Kimi K3.1 on release day, and DeepSeek-V4-Flash and Kimi K3.1 on AMD MI355X, with code in Inferact/zero-mismatch-rl and NVIDIA-NeMo/labs-molt.

    Vì sao đáng chú ý: NVIDIA Research and Inferact split the async RL rollout-learner gap into weight lag and kernel mismatch, showing that aligning kernels lets unclipped importance sampling hold stable training at policy lag 64.

  2. OpenClaw Blog69

    OpenClaw releases Multiplayer for shared agents and context

    OpenClaw has released Multiplayer, a free and open-source feature that lets multiple people connect to the same OpenClaw agent and workspace, with prompts appearing live across laptops and requests coordinated through a shared queue. In demos at GitHub Universe in San Francisco, two attendees edited the same 3D scene by typing prompts on separate machines without restating context. The OpenClaw Foundation says it has had 50+ people collaborating in the same shared environment and is continuing to expand the feature.

    Vì sao đáng chú ý: OpenClaw 把多人共享同一 Agent 与上下文做成免费开源功能，为团队协作中反复重建上下文的问题提供了一种可迁移的做法。

5 tháng 11Thứ Năm
  1. Preferred Networks News71

    PFN releases PLaMo 3 Translate open-weight translation LLM for edge devices

    Preferred Networks released PLaMo 3 Translate, a translation-specialized LLM used in its PLaMo Translation service, as an open-weight model on Hugging Face on November 5. 8B, 2B, 8B and 31B) and supports 53 languages including Japanese and English, running on smartphones, laptops and internal servers without a cloud connection.

    Vì sao đáng chú ý: PFN releases a translation-specialized LLM in four sizes from 0.8B to 31B, letting companies and individuals run 53-language translation on-device without cloud access.