GitHub Repo

GitHub 熱門專案、開源工具、框架、runtime 與重要 release。

Marin Launches Open Training of a 535B-A23B Model, Publicly Trackable Across 11 GB200 NVL72 Systems

Marin has begun training a mixture-of-experts (MoE) model with 535B total parameters and approximately 23B active parameters per token. The project plans to use 11 GB200 NVL72 systems to process roughly 18T to 18.75T tokens. Configurations, scaling experiments, and real-time telemetry are public, but model quality, the long-context strategy, and the final token budget have yet to be finalized.

2026-08-23

DeepSeek V4-Flash-Vision-Exp Adds Image Input and a 1M-Token Context Window, but Remains an Experimental API

DeepSeek has added image understanding to V4-Flash, supporting text and images through three compatible interfaces while retaining the existing Flash pricing. However, its officially reported agent benchmark results have yet to be independently reproduced, and neither the model weights nor the vision architecture has been disclosed.

2026-08-23

代理工具

OpenViking 0.4.16 Enables VikingBot to Load Skills Remotely and Removes the Resource Relations API

The new release integrates centralized agent skill storage, search, and caching into VikingBot, while adding per-user memory retrieval policies and persistent background imports. The upgrade also removes the experimental relations API and CLI commands, requiring existing integrations to migrate first.

2026-08-23

推論系統

SGLang 0.5.18 Overlaps Weight Loading with CUDA Graph Capture, Cutting Qwen3-32B Cold Start to 35.6 Seconds

The new release processes checkpoint staging and CUDA Graph capture concurrently during startup, delivering a 2.38× speedup over the standard default workflow in official H100 testing. It also rewrites parts of the tensor-parallel communication path and adds seven model families, but the Torch upgrade and cache-path consolidation introduce migration costs.

2026-08-23

代理工具

ASR Benchmark Fitting Quantified with Three Probe Types; Some Models Reproduce Erroneous Reference Transcripts 18% to 30% of the Time

Hume AI and Hugging Face found that when audio conflicts with the answers in public test sets, some high-scoring speech models still output content from the reference transcripts. The Open ASR Leaderboard has added a Benchmark Fitting tab, but these behaviors do not prove that the models directly encountered the test data.

2026-08-23

硬體

Needle 2 Compresses a 45M-Parameter Tool Model into 14MB and Constrains On-Device Calls with Schema Grammars

Cactus Compute recently improved Needle 2’s Python API, cross-platform execution, and Apache 2.0 licensing, while continuing to update its model card. It performs tool selection and structured extraction with 28MB of peak memory, although its speed and accuracy claims still come primarily from official tests.

2026-08-23

AI 安全

Semantica 0.6.6 Blocks SSRF, Injection, and Credential-Leak Paths in Agent Knowledge Pipelines

Semantica 0.6.6 delivers a concentrated set of fixes for multiple vulnerability classes affecting knowledge graph imports, backups, exports, and external requests, and its maintainers recommend that all deployments upgrade. The release also adds a fact-retraction mechanism that preserves provenance records, along with CrewAI integration.

2026-08-23

推論系統

Yutori Reveals Browser Agent Inference Architecture: 100K-Token Inputs, Short Tool Outputs, and Prefix Caching to Reduce Per-Step Costs

Yutori’s Navigator calls a vision-language model dozens of times during each browser task, with historical context growing to roughly 100K tokens. Together AI handles this workload using vLLM prefix caching and separate latency targets, although the claimed 2× speedup and 4–5× lower cost remain vendor-reported comparison results.

2026-08-23

代理工具

Hermes Agent 0.20.5 Adds Keyless Search Across Five Providers and Per-Task Reasoning Effort for Scheduled Jobs

Nous Research has rolled keyless web search, persistent memory for scheduled tasks, and execution-stall safeguards into Hermes Agent 0.20.5. Although labeled a patch release, it merges roughly 323 PRs; full migration notes will not arrive until 0.21.0.

2026-08-23

推論系統

Diffusers 0.40 Stabilizes the Modular Pipeline API While Removing JAX/Flax

Hugging Face now lets MiniMax H3, MiniMax Music 3, and Wan-Animate-2 plug in directly as composable blocks, without traditional DiffusionPipeline wrappers. The release also adds limited tensor parallelism, low-bit quantization backends, and security fixes, but removes Flax and changes LoRA outputs.

2026-08-23

推薦系統

NVIDIA Rewrites KV and Beam Search for Its Generative Recommendation Stack, Making 5K-Context Inference 2.27× Faster

NVIDIA has assembled HSTU, dynamic embeddings, and Semantic ID-based generative recommendation into an executable PyTorch reference stack. It rewrites the caching and decoding paths for recommendation workloads characterized by long histories, generation of only a few tokens, and extremely large beam widths, though the results are currently limited to NVIDIA hardware and synthetic configurations.

2026-08-22

推論系統

LFM2.5 Adds DSpark Draft Models, Boosting H100 Decoding Throughput by Up to 3.18×

Liquid AI has released DSpark draft checkpoints with about 300 million parameters for three LFM2.5 models and integrated them with llama.cpp and SGLang. Official tests show that acceleration varies significantly by model, data distribution, and hardware, so peak results should not be treated as representative of gains across all workloads.

2026-08-22