Register and share your invite link to earn from video plays and referrals.

Search results for DeepIn
DeepIn community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including DeepIn
DeepInfer math just made me realise closely trailing SOTA is a super smart feature, not a bug. FUCKKKK - these guys are way too smart!!! Had to write it all down - a short article - enjoy!
Show more
DeepSeek just open-sourced DeepInfer 🐋 the engine behind their own production API • Built for V4.1 Flash (1017) • DSpark speculative decoding • Deterministic outputs • Apache 2.0 Catch: SM100 Blackwell or Huawei Ascend only. No DGX Spark yet 👀
Show more
Pay attention to people who seethe at or pooh-pooh DeepInfer. No matter what reason they give or how technical they speak. Non-credible voices
っ◔◡◔)っ 𝘾𝙤𝙢𝙞𝙣𝙜 𝙨𝙤𝙤𝙣⠀⠀ ⠀⠀ 🌈 Title: #DeepIn# ⠀ 🔔 International Premiere: June 26, 2026⠀ ⠀ ⭐Starring: ⠀ Ollie Shu Yuan ⠀⠀ 🌎Rest of the world (except Americas, Europe, Middle East, Oceania, India, Japan, & Korea)⠀ ⠀ #入戲#
Show more
DeepSeek open-sourced the inference engine behind its own production AI service. DeepInfer is the framework DeepSeek uses to serve V4.1 Flash and they're giving away production tricks such as ⚡ DSpark speculative decoding 🧠 confidence-scheduled verification 📚 SWA bounded replay ⚙️ asynchronous scheduling 🧩 MoE expert parallelism + load balancing 🎯 structured JSON / regex / grammar output 🔬 deterministic + batch-invariant inference Plus DeepSeek's own stack of FlashMLA + DeepGEMM + DeepEP + DeepSelect + custom TileLang kernels DeepSeek says that future model inference code + new optimizations will land on this stack too. This is basically a look inside the code DeepSeek uses to make its enormous models practical to host. So now other inference harnesses can study the production implementation. ⚠️ Right now DeepInfer supports only ❌ no consumer NVIDIA GPUs ✅ NVIDIA SM100 ✅ Huawei Ascend 950 So this isn't Local AI yet. GH link in ALT
Show more
We got cited in the official NVIDIA blog alongside @perplexity_ai @ClickHouseDB and @DeepInfra for the performance results with NVIDIA's new Vera CPU. A couple of weeks ago, the @daytonaio team spent 5 days onsite at @nvidia HQ putting the Vera CPU through agentic workloads on Daytona sandboxes. Results: - serious gains for agentic execution - larger memory bandwidth than traditional server CPUs - wide SVE2 vector units with native FP8 that make NumPy-heavy code fly Agentic workloads have a completely different shape from standard inference. A single session can accumulate hundreds of thousands of input tokens as agents reason, call tools, and spawn sub-agents. That's the same workload profile we've been optimizing Daytona sandboxes for: stateful, long-running, and CPU-heavy vs quick ephemeral containers most people are still building on. Vera is built for this. And Daytona is already ARM-capable, with ARM64 sandboxes rolling out globally soon. Read more:
Show more
DeepSeek just open sourced its high-performance, large-scale inference framework DeepInfer in Apache-2.0 license. Supported features: - Optimized kernels, model and sampler runtime - Parallelism: Attention DP / balanced CP, MoE EP + EPLB - DSpark and confidence-scheduled verification - SWA bounded replay - Asynchronous scheduling (zero-overhead batch scheduler) - Batch-invariant inference - Deterministic sampling - Structured output
Show more
0
212
2.6K
210
Forward to community
Video and audio, from one model. Wan3.0-Video from @Alibaba_Wan is now on DeepInfra: 30-second clips at 1080P, omni-modal reference (images, files, even web pages), and characters that stay the same character. $0.20/sec →
Show more
Open-source AI stack from DeepSeek for building your own agent: ▪️ DeepSeek Harness (dsh): Connects a model to tools and manages agent sessions. ▪️ DeepSeek-V4.1-Flash and other models ▪️ DeepInfer: An inference engine for running models. ▪️ 3FS: A distributed file system for storing and moving data ▪️ deepseek-recipe: Translates API requests into model prompts and parses responses ▪️ FlashMLA: Optimized attention kernels ▪️ DeepGEMM: Optimized GPU kernels for matrix operations ▪️ DeepEP: Moves data between accelerators ▪️ DeepJIT: Compiles, caches, and loads GPU kernels at runtime ▪️ TileKernels: Optimized kernels for operations like routing and quantization Read our full guide to how the pieces work and fit together, what it takes to run them, and what’s still missing from the stack:
Show more
The Art of Living has Contributed Enormously for Humanity, Inner Evolution & Spiritual Development. The Number of Lives they Impact is Huge. Great to see Temple Founder Deepinder ji seeking Within ❤️ #FI#
Show more