我的收藏提交工具
FOXAI SEARCH

全站搜索

新闻报道 941

v0.43.0

## What's Changed * model_prefetch: syncrhonize all graph cleanups by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17178 * Add rope scaling support to MOSS-image by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17172 * [Partner Nodes] Renew partner-node sign-in tokens in API nodes by @dante01yoon in https://github.com/Comfy-Org/ComfyUI/pull/16943 * [Partner Nodes] feat(HeyGen): add HeyGen Voice instant clone and text-to-speech by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17043 * [Partner Nodes] feat(ClarityAI): add Crystal Video Upscaler node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17192 * [Partner Nodes] feat(BFL): add 2K/4K resolutions to FLUX 3 Video nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17200 * Support MOSS-image

翻译服务暂未运行,当前显示原文。
ComfyUI 发布

b11928

model: Add MiniCPM-OCR-Jev (#30980) * model : add MiniCPM-OCR-Jev support The model is a Qwen3.5-VL trunk with a value head read at the last token: it scores an OCR text against an image rendered from it, it does not generate. Add the openbmb-minicpm-ocr-jev decision type, served by POST /v1/systemone. The class scores are the pooled output of the sequence, read with last pooling, so the conversion turns score.weight into cls.output and sets embedding_length_out. The checkpoint has no LM head, so text generation is rejected instead of using the output weights duplicated from the token embeddings. The task is fixed, so its prompt is entirely in the systemone template, the same way h2o-lightning keeps its default there. The processor of the checkpoint allows up to 16384 merged tokens per ima

翻译服务暂未运行,当前显示原文。
llama.cpp 发布

n8n@3.0.0

# [3.0.0](https://github.com/n8n-io/n8n/compare/n8n@2.45.0...n8n@3.0.0)(2026-10-27)### 问题修复 * 在工件下载按钮上添加文件类型提示工具提示([#41490](https://github.com/n8n-io/n8n/issues/41490))([4a74f02](https://github.com/n8n-io/n8n/commit/4a74f027e612f31098b354dd3a77b2c2ab98281c)) * **ai-builder:** 检查执行权限:在 Assistant 执行读取时进行检查([#41863](https://github.com/n8n-io/n8n/issues/41863))([a967486](https://github.com/n8n-io/n8n/commit/a9674866d075e989a5ce896432262c9a7dc8b0c7)) * **ai-builder:** 通过已配置的 AI 传输通道发送 Assistant 模型调用([#41948](https://github.com/n8n-io/n8n/issues/41948))([9b63561](https://github.com/n8n-io/n8n/commit/9b63561cbb48f06d216f27be3b77722d97e4e74a)) * 支持自定义 OAuth2 范围([#41249](https://github.com/n8n-

n8n发布

将Transformer理论付诸实践

arXiv:2610.32104v1 发布类型:新 摘要:为刻画Transformer架构的能力与局限性,人们已发展出若干形式化理论,这些理论分别采用不同的抽象方法,以捕捉该架构的不同特性。由于其底层假设与概念框架存在差异,这些理论在预测Transformer对哪些任务感到容易或困难时往往意见不一。我们梳理了七种关于Transformer能力的理论(Star-free、$\mathsf{AC}^0$、$\mathsf{TC}^0$、C-RASP、MPC、BAPO以及敏感性),并将其研究结果转化为一张通用的预测矩阵,覆盖一系列涉及不同计算结构的任务。我们还提供了新的理论成果,以完善这一矩阵。随后,我们对这些理论进行评估

arXiv cs.LG

DualPace:用于大语言模型推理的解耦调度与GPU-CPU协同解码

arXiv:2610.33501v1 发布类型:新 提要:大型语言模型(LLM)的推理服务依赖于批处理以提升推理吞吐量,但键值(KV)缓存会随序列长度增长,从而限制了GPU上的并发度。通过CPU卸载,可以利用主机内存扩展KV缓存容量,然而现有系统在很大程度上仍受GPU瓶颈制约:只有当GPU调度器能够提供合适的重叠机会时,CPU驻留的请求才能取得进展。因此,主机内存与CPU计算无法作为独立的推理资源发挥作用,导致负载下CPU端进度波动加剧,并使尾部词间延迟(ITL)显著增加。我们提出了DualPace,一种将主机转变为独立调度解码引擎的LLM推理运行时。DualPace在两个引擎之间划分了调度权:GPU引擎

arXiv cs.DC

b11923

ggml : relax scale to non-contiguous views (#31146) * ggml : relax scale to non-contiguous views SCALE requires src0 to be 1D-contiguous. Relax this to dim-0 contiguity with arbitrary row strides (ggml_is_contiguous_rows), same as the unary ops in the Metal backend. - ggml: relax the assert in ggml_scale_impl - cpu: address src0 rows through their byte strides (f32, bf16) - cuda: stride-aware kernel, fastdiv row decomposition - metal: support bf16 scale (guarded unary instantiations) - sycl: keep the gate at contiguous, the kernel is flat f32 Add view variants to test_scale. Verified on CPU, Metal and CUDA. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (RTX 5090 32GB, DDR5 128GB) * cuda : skip the softcap fusion on non-contiguous views The fused softcap kernel reads src and w

翻译服务暂未运行,当前显示原文。
llama.cpp 发布