Alibaba unveils Zhenwu V900 AI accelerator, claims it's 'the most powerful AI chip in China'

Tom's Hardware 显卡与工作站 · 来源更新 2026/09/23 21:21

今日摘要使用自己的 API，仅供个人查看

来源摘要

Alibaba’s T-Head Zhenwu V900 claims three times the M890’s performance with 216GB of memory as Alibaba targets 10T-parameter Qwen Shane has a background in computer engineering and has worked as a freelance consultant in multiple industries. He has a strong affection for history and loves to game. He worked his way up from a Commodore 64 and has always been interested in technology and writing. He particularly enjoys breaking down complex concepts into understandable ideas. He’s a lifelong East-coaster and animal-lover.

阅读原始来源

来源: Tom's Hardware 显卡与工作站 · 媒体报道
来源发布: 2026/09/23 20:00
来源更新: 2026/09/23 21:21
首次采集: 2026/09/23 23:59

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。

Qwen · 通义千问动态

llama.cpp 发布: b11138

jinja : parse unary +/- before variables (#29244) * jinja : parse unary +/- before variables Lexer already emits unary_operator for -n / +n, and runtime executes unary -. Parse them at multiplicative precedence so slices like items[:-n] and GigaChat indent[:-i

来源更新 2026/09/23 23:39国际查看原文

算力与芯片NVIDIA 官方博客官方来源

Sakeena Fiza Helps NVIDIA Hardware Succeed at Scale

When Sakeena Fiza describes her work as a validation engineer at NVIDIA, she does so in terms more befitting a detective story than a world-class engineering lab. “Validation engineers look in the shadows and shine a light into every corner,” Fiza said. “Every

发布 2026/09/23 23:00国际查看原文

算力与芯片llama.cpp 发布官方来源

llama.cpp 发布: b11136

server: accept OpenAI video_url content type and data: video URIs (#27921) The OpenAI chat completions API specifies content part type "video_url" with a {"url": ...} object, and clients typically send data: URIs (e.g. data:video/mp4;base64,...). The llama-ser

来源更新 2026/09/23 22:46国际查看原文

算力与芯片IT之家 AI 与硬件媒体报道

爆料称 AMD 为微软 XBOX Helix 和索尼 PS6 主机设计的芯片已流片，前者浮点算力纸面领先四成

IT之家 9 月 23 日消息，据外媒 Wccftech 今天（23 日）晚间报道，AMD 爆料者 Kepler_L2 透露，AMD 为 PlayStation 6 和 XBOX Helix 设计的芯片现已完成流片，两款主机有望明年年底发售。 Kepler 与另一名博主“摩尔定律已死（下称 MLID）”此前都否认了延期说法，理由是生产合同基本敲定，芯片据称计划在明年第二季度投产，推迟生产的代价甚至比承担内存涨价的成本更高。 Kepler_L2 还确认了一组看似接近最终规格的浮点算力数据：PS6 为 40TFLOPS

发布 2026/09/23 22:34国内查看原文

算力与芯片llama.cpp 发布官方来源

llama.cpp 发布: b11135

server: Dedup the draft HF model via dedup-cache-models (#27934) * server: Dedup the draft HF model via dedup-cache-models Fixes #27846 * server: avoid capturing structured binding in lambda **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Sili

来源更新 2026/09/23 22:08国际查看原文