算力与芯片官方来源国际

llama.cpp 发布: b11075

llama.cpp 发布 · 来源更新 2026/09/22 00:46

今日摘要使用自己的 API，仅供个人查看

来源摘要

ggml-metal : simplify fusion pattern op list declaration (#29206) * ggml-metal : derive non-empty fusion ops from ops_all Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * ggml-metal : drop _all suffix from fusion op pattern vectors Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-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.cpp/releases/download/b11075/llama-b11075-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11075/llama-b11075-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11075/cudart-llama-b11075-bin-ubuntu-cuda-12.8-x64.tar.gz) - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/r

阅读原始来源

来源: llama.cpp 发布 · 官方来源
来源发布: 2026/09/22 00:43
来源更新: 2026/09/22 00:46
首次采集: 2026/09/22 05:59

本文为公开信息索引与摘要，详情及后续变化请以原始来源为准。

DeepSeek · 深度求索动态 Meta · Llama 动态 NVIDIA · 英伟达动态 Intel · 英特尔动态

更多算力与芯片

算力与芯片NVIDIA 开发者官方来源

Simplifying Model Serving Across Multiple GPUs with NVIDIA TensorRT Multi-Device Integration in NVIDIA Dynamo-Triton

The compute and memory demands of generative AI increasingly exceed what a single GPU can provide. NVIDIA TensorRT multi-device inference is a new capability...

来源更新 2026/09/22 05:51国际查看原文

算力与芯片llama.cpp 发布官方来源

llama.cpp 发布: b11081

test-llama-archs : make tensor data stdev configurable and improve help (#29133) * test-llama-archs : make tensor data stdev configurable Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * test-llama-archs : expand usage and add examples Assisted-by: pi:

来源更新 2026/09/22 03:54国际查看原文

算力与芯片llama.cpp 发布官方来源

llama.cpp 发布: b11080

tests/test-backend-ops : allow regex entries in the -o filter (#29204) * tests/test-backend-ops : allow regex entries in the -o filter so far -o only accepted a comma separated list of exact op names or full test case strings. entries that are not plain op nam

来源更新 2026/09/22 03:21国际查看原文

算力与芯片llama.cpp 发布官方来源

llama.cpp 发布: b11078

args: add env vars for temperature, top-p, min-p and penalties (#27380) Allow configuring --temp, --top-p, --min-p, --repeat-penalty, --presence-penalty and --frequency-penalty via LLAMA_ARG_* so llama-server can be fully controlled from an EnvironmentFile (e.

来源更新 2026/09/22 02:52国际查看原文

算力与芯片NVIDIA 开发者官方来源

Benchmarking LLM Inference at Scale with AIPerf

You’re deploying a model on a system. It starts up, prompts are getting responses. Now the hard question: Is this fast? Your instincts might lead you to send...

来源更新 2026/09/22 02:45国际查看原文