我的收藏提交工具
FOXAI SEARCH

全站搜索

新闻报道 252

inference-systems

b11877

vulkan: Add a larger tile size for conv3d (coopmat2 only) (#29920) * vulkan: Add a larger tile size for conv3d (coopmat2 only) This adds a larger tile size, in practice it is only for coopmat2 where we don't need shared memory to store the output (would use more than 64KB). Add some additional representative backend tests. At least, this is what codex came up with from looking at sd.cpp Wan VAE. * only apply large tile size for newer driver versions **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11877/llama-b11877-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama

翻译服务暂未运行，当前显示原文。
llama.cpp 发布
行业动态

Introducing Kimi K3.1 Pro

Introducing Kimi K3.1 Pro Kimi K3.1 Pro landed on the Kimi API today - it's not yet open weights, but Moonshot promise "Full model weights will be released by Nov 4, 2026". They're also offering a "Highspeed" version that's 2-3x faster, at twice the price (except for input token cache hits, which are priced the same). The US dollar pricing is $2.00/million tokens for input and $10/million for output - the same as GPT-6.1 Sol and half the price of Claude Opus 5.5. Moonshot's own benchmarks show Kimi as approximately level with Opus 5.5 and GPT-6 Astra - beating them on a few benchmarks, coming close on others. Artificial Analysis scored Kimi at 55 - ahead of Claude Fable 5.1, GPT-6 Astra, and Gemini 4 Argon (all at 53) and behind only Claude Opus 5.5 (58). This is the first time a (soon-to-

翻译服务暂未运行，当前显示原文。
西蒙·威利森
研究进展

IBM发布Granite时序集成预测模型：四模型零微调组合，提供稳健默认预测方案

IBM Research推出开源的Granite Timeseries Ensemble（v1），集成PatchTST-FM-r1/r2、FlowState与Tiny Time Mixers四类预训练架构，支持零微调下的概率性集成预测；默认采用等权概率池化（Probabilistic Ensemble），亦提供基于四分位距自适应加权（IQR Ensemble）；在GIFT-Eval基准（截至2026-10-20快照）上，其点预测误差（MASE=0.683）略优于最佳单模型，整体鲁棒性显著提升。

Hugging Face 官方博客
行业动态

i14发布Laplace 3B线性注意力模型：基于AWS Trainium2与原生PyTorch实现固定状态内存推理

i14推出30.28亿参数的Laplace 3B模型，采用门控线性注意力（GLA）替代Softmax注意力，其推理时每序列递归状态恒为29.5 MB，与上下文长度无关；该模型在单台AWS trn2.48xlarge（16颗Trainium2芯片）上完成训练与服务验证，训练吞吐达12万token/秒，服务吞吐11544 output token/秒（1280并发序列），所有性能数据均为i14与AWS GenAIIC团队内部实测结果。

AWS Machine Learning Blog
行业动态

llm-echo 0.5

发布：llm-echo 0.5 我正在筹备一个新的LLM版本，而在测试Pull Request时，我又重新审视了llm-echo调试插件。这个插件提供了一个“模型”，它完全不涉及任何LLM——只是原样回显输入的提示内容。新版本现已更新了模拟的token使用统计，将工具调用、系统提示以及推理token都纳入考量。示例用法如下：uvx --with llm-echo llm -m echo 'hi there' -o thinking 1 --usage 输出结果： 首先我考虑提示内容，然后决定该说些什么。{ "prompt": "hi there", "system": "", "attachments": [], "stream": true, "previous": [] } Token使用情况：输入2个，输出24个 标签：llm

西蒙·威利森
行业动态

Anthropic tells investors quarterly revenue up nearly 50% to $16.8bn ahead of IPO

Anthropic tells investors quarterly revenue up nearly 50% to $16.8bn ahead of IPO The phrase "told investors" appears four times in this FT article, which reports on Anthropic's day of hosting investors on Wednesday. Lots of details in here from "people with knowledge of the matter". Key things I learned from the article: Q1 revenue (Jan/Feb/Mar) was "about $4.8bn" Q2 (Apr/May/Jun) was $11.5bn Q3 (Jul/Aug/Sep) was $16.8bn In Q3: $1.70 in revenue for every $1 spent on "computing power" Adjusted operating margins (excluding stock-based compensation) were 11% This point about distillation is worth quoting in full (highlight mine): The start-up has also clamped down on “distillation” — a controversial practice whereby rival AI labs train their models on the outputs of more advanced ones. When

翻译服务暂未运行，当前显示原文。
西蒙·威利森
行业动态

llm-gemini 0.35

Release: llm-gemini 0.35 I added support to llm-gemini for the new Gemini 4 Argon model, made available today via the Gemini API and for customers of their $100/month subscription plan. Here are the low, medium and high pelicans. As expected, they are all excellent: Gemini has a track record of producing great SVGs, and are the only lab where I know their staff have invested in SVG specifically (and who have boasted about their pelicans before.) Here's the "high" illustration, which cost me 17.166 cents: The pricing is interesting. At launch, Argon is $2/million input and $10/million output - the same price as GPT-6 Sol, half the price of Claude Opus 5.5 and 1/5th the price of Claude Fable 5.1 and GPT-6 Astra. But on December 1st Argon is set to double in price - so it will be the same pri

翻译服务暂未运行，当前显示原文。
西蒙·威利森