Seapy retweeted
Save this post, the Bambu Lab Black Friday Playbook is here.
Beyond our best prices of the year and the 28 × H2C Combos giveaway on the official store, we're dropping a massive prize pool right here:
• 5 × Bambu Lab H3C (yes, our brand new H3C!)
• 20 × 4-Color Filament Bundles
• 50 × $50 Bambu Lab Store Coupons
• One Ultimate Grand Prize (revealed tomorrow)
You might want to clear some space in your workshop...
#BambuLab #BlackFriday #3DPrinting
RTX Pro 6000 x 4 에서 속도가 빨라진다고 해서 올려봤는데, 생각보다 개선은 적었습니다.
DeepSeek-V4.1-Flash-1017 공식 가중치 그대로, 기존 vLLM 대비 단일 스트림
· JSON 구조화 출력 400 → 519 tok/s
· 코드 418 → 546
· 문장 201 → 226
원글의 750까지는 안 나왔어요. 제 장비는 Max-Q라 300W 전력 제한이 있고 메모리 OC도 안 해서 그런 것 같습니다. 동시 요청에서 문장 생성은 오히려 10~14% 느려지기도 해서 운영 전환은 우선 지켜보기로 했어요.
그래도 같은 GPU, 같은 가중치인데 커널 최적화만으로 25~40%가 빨라지는 걸 보면 소프트웨어 쪽 업사이드가 아직 꽤 크다는 생각이 드네요.
레시피 공유해주는 분들에게는 항상 감사합니다.
적용한 레시피 : github.com/kacper-daftcode/v…
Seapy retweeted
$TSLA
BREAKING: Turo and Tesla just announced the first verified Tesla FSD(Supervised) rental experience in the U.S., launching October 28.
• For guests: You can search for and book Teslas with FSD (Supervised) activated. FSD status is verified through a direct Tesla API integration.
• For hosts: Once a host links their Tesla account to Turo, FSD status is verified automatically and shown on eligible listings. Eligible U.S. hosts also get a free one-month FSD (Supervised) trial.
• Scale: Thousands of FSD-enabled Teslas are already on Turo. The Model 3 and Model Y are the 3rd and 4th most popular models on the platform this year.
• CEO quote: Turo CEO Andre Haddad says 55% of Americans, and 71% of Gen Z, are interested in self-driving tech for travel.
Seapy retweeted
[New Post] 3D 프린터로 만든 10인치 서버 랙
blog.outsider.ne.kr/1816
아마존에서 삼성 990 PRO 2테라도 할인 하네요. 4테라 할인도 아직 유지 중이고요. 일시적인건지 계속 할인인지 모르겠어요. link.amazon/B00PJsYMq
Seapy retweeted
Kimi K3.1 Pro 翻车了
MiniMax M3.1 Flash 翻车了
Muse wonder 翻车了
Gemini 4 Argon 也翻车了
只有 Deepseek V4.1 Flash 1017
大家边夸边用
Seapy retweeted
"The pace, and the expectations that came with it, felt almost as jarring [in China] compared with America as America's pace does compared with Europe. Everyone was just on it, all the time." world.hey.com/dhh/seven-year…
Seapy retweeted
Worst idea of the day goes to governmental official of relatively small country who suggested they would require AI companies to publicly disclose to their product safety commission within 24 hours of discovery all software vulnerabilities. 🤦🏻♂️🙅🏻♂️☠️
gx10 의 1TB 용량이 예전에는 쓸만 했는데 DeepSeek v4.1 flash 오면서 용량이 부족하네요. 가중치가 470기가, engram, 도커 이미지등...
Minimax M3.1 flash 테스트 하려고 모델 복사할 공간도 없음 ㅜㅜ SSD 업그레이드 해야되나봐요.
Seapy retweeted
🎉 MiniMax M3.1 Flash from @MiniMax_AI has Day-0 support in vLLM!
Built for multi-step automation, real-codebase engineering and visual reasoning—with native NVFP4 KV, NVFP4 MoE weights and DSpark speculative decoding in the serving stack.
What the model can do, and the vLLM engineering that makes it practical to serve. 👇
Model: huggingface.co/MiniMaxAI/Min…
1/5
MiniMax M3.1 Flash weights are now public. 428B parameters total, 23B activated per token.
Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym.
Efficient by design: MiniMax Sparse Attention and DSpark speculative decoding improve inference efficiency.
Hugging Face:
huggingface.co/MiniMaxAI/Min…
ModelScope:
modelscope.cn/models/MiniMax…
API: platform.minimax.io
M Plan: minimax.io/m-planMiniMax
MCode for desktop: agent.minimax.io/download
