Aaron (@lowstz) 's Twitter Profile
Aaron

@lowstz

如果在这里退缩了一步,那么过去那些重要的誓言、约定,就全部会消失不见,而我再也无法回到这里了。

ID: 133778771

linkhttps://github.com/lowstz calendar_today16-04-2010 16:11:11

23,23K Tweet

1,1K Followers

1,1K Following

Aaron (@lowstz) 's Twitter Profile Photo

数值计算 deepseek 深怕出错会 reasoning 确认多次,特定场景 deepseek 搜索结果准确率更高, gemini 5 次错 2 次

Qwen (@alibaba_qwen) 's Twitter Profile Photo

🚀 Introducing Qwen3-Omni — the first natively end-to-end omni-modal AI unifying text, image, audio & video in one model — no modality trade-offs! 🏆 SOTA on 22/36 audio & AV benchmarks 🌍 119L text / 19L speech in / 10L speech out ⚡ 211ms latency | 🎧 30-min audio

🚀 Introducing Qwen3-Omni — the first natively end-to-end omni-modal AI unifying text, image, audio & video in one model — no modality trade-offs!

🏆 SOTA on 22/36 audio & AV benchmarks
🌍 119L text / 19L speech in / 10L speech out
⚡ 211ms latency | 🎧 30-min audio
Aaron (@lowstz) 's Twitter Profile Photo

当时买只是觉得中芯国际高端制程良率低,测试设备短缺,没想到这帮做测试设备的业绩居然这么好

当时买只是觉得中芯国际高端制程良率低,测试设备短缺,没想到这帮做测试设备的业绩居然这么好
vLLM (@vllm_project) 's Twitter Profile Photo

Pro Tip💡Fast and simple way to deploy DeepSeek-V3.1-Terminus with vLLM ⚡️ Run it with: vllm serve deepseek-ai/DeepSeek-V3.1-Terminus -tp 8 -dcp 8 (as simple as appending -dcp 8 after -tp 8) Thanks to the Kimi.ai team, vLLM 0.10.2 adds Decode Context Parallel (DCP)

Pro Tip💡Fast and simple way to deploy DeepSeek-V3.1-Terminus with vLLM ⚡️

Run it with:
vllm serve deepseek-ai/DeepSeek-V3.1-Terminus -tp 8 -dcp 8
(as simple as appending -dcp 8 after -tp 8)

Thanks to the <a href="/Kimi_Moonshot/">Kimi.ai</a> team, vLLM 0.10.2 adds Decode Context Parallel (DCP)
Benjamin Wiley (@prof_wiley) 's Twitter Profile Photo

2015-02-18 — 🔵 US bans Intel Xeon Phi processors to Chinese supercomputing centers 2015-03 — 🔴 China 13th Five-Year Plan makes semiconductors a national priority 2018-10-30 — 🔵 US bans Fujian Jinhua DRAM memory chips 2019-05-16 — 🔵 US bans Huawei from Qualcomm Snapdragon