PCIe显卡经内核与通信重构优化，DeepSeek推理吞吐提升近7倍
该动态指出通过内核补齐与通信重构等优化手段，PCIe显卡在运行DeepSeek模型时的推理吞吐量提升了近7倍，并声称1.5台6000D设备的表现可超越1台B300。需要说明的是，素材提供的信息较为简短，缺少具体的软硬件环境、完整测试基准以及技术实现的深度细节。
DC AI 热点
全部 AI 动态
9月24日2026-09-24
早报｜iOS27测试版新功能可阻止摇一摇广告/5999起，小米18 Pro发布/宾利发布首款纯电车Torcal，888马力
· DeepSeek 发新论文，公开 Agent 训练沙箱 DSec · 蔚来 ES9 交付达 3 万台，用时 119 天 · iPhone 18 Pro 用户反映夜景照片出现「绿影」 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
9月23日2026-09-23
刚刚，GPT-6 新模型掀桌！「白菜价」杀进 DeepSeek 腹地
DeepSeek 的价格护城河，迎来 OpenAI 的挑战 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
9月22日2026-09-22
v0.30.0
v0.30.0 Highlights This release features 762 commits from 315 contributors (104 new)! New models : DeepSeek-V4.1-Flash ( #56214 , #56228 , #56208 ) with the whole KV stored in MXFP8 through the FlashMLA V4.1 record on SM100 ( #56893 ), DeepGEMM Mega-mHC ( #56962 ), and async Engram prefetch with Engram DP sharding ( #56512 ); DeepSeek-V4-Flash-Vision-Exp ( #54566 ), also on ROCm ( #55107 ) and with LoRA ( #55897 ); GLM-5.3-Flash ( #53906 ) with EPLB ( #55119 ); K2-Horizon ( #55063 ); Cohere Compass ( #54774 ); Bailing V3 VL ( #55921 ); Nanbeige4.2 via the Transformers backend ( #56071 ); and a DeepSeek-V4 CPU backend with AVX512/AMX sparse ML
9月10日2026-09-10
Release 5.17.0
Release v5.17.0 New Model additions HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared expert and routes every token to 8 of them. The context window is 1M tokens. The architecture combines four features: Multi-head Latent Attention (MLA) compresses keys and values into a low-rank latent ( kv_lora_rank ) that kv_b_proj expands back to one key/value per query head. DeepSeek Sparse Attention (DSA) selects index_topk keys per query with a lightweight indexer. Following IndexShare , only the layers marked "full" in in