IndustryOfficial11月5日 10:29

Huawei Ascend 为 Kimi K3.1 Pro 提供首发日支持

Huawei Ascend Adds Day-Zero Support for Kimi K3.1 Pro Across Atlas A3 and Ascend 950 SuperPoDs

官方一手pandaily@[email protected] (Pandaily)

Blog/Media

Why we picked it

Kimi K3.1 Pro 这个 2.8 万亿参数模型发布当天就能在 Huawei Atlas 和 Ascend 950 SuperPoD 上跑，vLLM 和 SGLang 都适配了。

Moonshot AI 发布 2.8 万亿参数的 Kimi K3.1 Pro，Huawei 宣布其 Ascend 硬件在发布当天即可运行该模型。支持的硬件包括 Atlas 800 A3、Atlas 900 A3 SuperPoD 和 Ascend 950 SuperPoD。软件层面，vLLM Ascend 和 SGLang 两个推理框架同步提供适配。

Original · pandaily

Huawei Ascend Adds Day-Zero Support for Kimi K3.1 Pro Across Atlas A3 and Ascend 950 SuperPoDs

Huawei says vLLM Ascend and SGLang run Moonshot AI's 2.8-trillion-parameter Kimi K3.1 Pro on Atlas 800 A3, Atlas 900 A3 SuperPoD and Ascend 950 SuperPoD from launch day.

#Kimi K3.1 Pro #Huawei #Ascend #vLLM #SGLang

Keep reading

Recent stories with the same tag or section

Models Builders79°08:50

Chinese content华为昇腾 0 Day 适配 Kimi K3.1 Pro 推理部署

Kimi K3.1 Pro 发布当天昇腾就能跑推理了，2.8 万亿参数、百万上下文，用 vLLM Ascend 或 SGLang 可直接部署。

#Kimi K3.1 Pro #昇腾 #华为 #月之暗面

Event

IT之家2 sourcesSource

Models US vs ChinaMulti-source05:32

Chinese contentMoonshot 开放 Kimi K3.1 Pro 权重，登顶 Agent Arena 开源模型榜首

月之暗面把 K3.1 Pro 权重放出来了，Agent Arena 上开源第一，Shell 命令成功率和听指挥能力都涨了不少，玩开源智能体的可以试试。

#Kimi K3.1 Pro #Moonshot AI #Agent Arena #开源模型

Event

lmarena.ai@lmarena_ai7 sourcesSource

Models US vs ChinaSelected04:42

Kimi K3.1 Pro lands on Databricks at launch

Day-0 availability on Databricks signals Moonshot pushing Kimi into enterprise data platforms rather than consumer chat apps, putting it next to 70+ alternatives where procurement teams actually evaluate models. Unity Gateway means companies can A/B Kimi against rivals without code changes — useful for cost benchmarking. Enterprises with Lakehouse data estates, including those in Singapore and ASEAN running Databricks, can try it immediately.

#Kimi K3.1 Pro #Databricks #Moonshot (Kimi)#agents

官方账号Databricks@databricksSource

Models Builders77°04:39

Chinese contentKimi K3.1 Pro 权重上线 HuggingFace，3T 级参数开源

月之暗面把 Kimi K3.1 Pro 权重放到 HuggingFace 了，3T 参数的多模态智能体模型，能自己下载部署。

#Kimi K3.1 Pro #Moonshot #HuggingFace #开源模型

TestingCatalog@testingcatalogSource

Models BuildersMulti-sourceSelected02:23

Agent Arena data shows 66% cost gap in hour-long agent tasks

For hour-long agent workloads, the cheapest model is not automatically the right one: Claude Opus 5.5 scores higher but costs twice as much per hour as Gemini 4 Carbon. Teams running long-horizon agents can use these per-hour cost and time figures to match model choice to budget and quality needs. The 55-minute spread among frontier models also suggests task duration, not just accuracy, should enter model selection criteria.

#Claude Opus 5.5 #Gemini 4 Carbon #GPT-6 Astra #Kimi K3.1 Pro

Event

lmarena.ai@lmarena_ai11 sourcesSource