DCAI
DC AI 热点

全部 AI 动态

全部其他动态前沿研究与模型架构智能体与应用工程安全治理与商业生态算力与数据中心具身智能与智能硬件
全部语言仅中文10 条动态
来源筛选
全部来源AITNT · AI头条（网页）IT之家 · AI 筛选InfoQ · 架构与云计算Solidot · AI 筛选少数派 · AI 筛选爱范儿 · AI 筛选量子位阮一峰 · AI 筛选AWS News · 云基础设施AWS 机器学习Anthropic 官方动态（网页）Ars Technica · AI 筛选Azure Blog · 云基础设施CNCF BlogClaude Code 更新Cloudflare Blog · 网络基础设施Data Center DynamicsData Center KnowledgeGary MarcusGoogle AIGoogle DeepMindGoogle Developers · AI 筛选Google ResearchHugging FaceKubernetes BlogMIT Technology Review AIMicrosoft ResearchNVIDIA · AI 筛选Ollama 更新OpenAI 官方动态OpenStack BlogSebastian RaschkaServeTheHomeSimon WillisonTechCrunch AIThe DecoderThe Next PlatformThe Verge · AI 筛选Transformers 更新arXiv 人工智能arXiv 机器学习arXiv 自然语言处理vLLM 更新
9月23日2026-09-23
9月22日2026-09-22
vLLM 更新✦ 精选规则精选13:20

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

阅读原文 ↗# DeepSeek
9月19日2026-09-19
vLLM 更新✦ 精选规则精选05:15

v0.30.0rc2

[Bugfix][NIXL] Avoid receive reports for notification-only requests (…

阅读原文 ↗
9月17日2026-09-17
9月16日2026-09-16
9月13日2026-09-13
vLLM 更新✦ 精选规则精选02:42

v0.29.1rc0

[watermarking] Dual-key gumbel-max watermarking for speculative decod…

阅读原文 ↗
9月11日2026-09-11
vLLM 更新✦ 精选规则精选07:53

v0.29.0

v0.29.0 Highlights This release features 594 commits from 277 contributors (91 new)! Model Runner V2 is now the default for all models ( #53183 ), completing the rollout that began with pooling models ( #48290 ). MRV2 also gained CUDA graph memory profiling for KV cache auto-sizing ( #53306 ), batch-sharded sampling that cuts per-step logits memory by 1/TP ( #50465 ), prompt embeds ( #42963 ), extract_hidden_states speculation ( #49811 ), padded FULL cudagraph dispatch for uniform decode under spec decode ( #53407 ), and DP-sync skipping before EAGLE/MTP draft prefill ( #53694 ). MRV1 remains in use for a few ROCm models and features MRV2 doe

阅读原文 ↗
9月8日2026-09-08
vLLM 更新✦ 精选规则精选16:34

v0.29.0rc6

[Bugfix][Core] Apply dense prefix cache default to hybrid models ( #55 …

阅读原文 ↗