[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.] [LLMs](/topic/llms) ### Top Social Posts *Showing only X posts for non-authenticated requests. Use your API key in requests for full results.* "🚀 DeepSeek-OCR the new frontier of OCR from @deepseek_ai exploring optical context compression for LLMs is running blazingly fast on vLLM ⚡ (2500 tokens/s on A100-40G) powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to XX while keeping XX% OCR accuracy at XX. 📄 Outperforms GOT-OCR2.0 & MinerU2.0 on OmniDocBench using fewer vision tokens. 🤝 The vLLM team is working with DeepSeek to bring official DeepSeek-OCR support into the next vLLM release making multimodal inference even faster and easier to scale. 🔗 #vLLM #DeepSeek #OCR #LLM #VisionAI #DeepLearning" [X Link](https://x.com/vllm_project/status/1980235518706401405) [@vllm_project](/creator/x/vllm_project) 2025-10-20T11:31Z 19.9K followers, 3311 engagements "most LLMs have problem with word count. I asked for 2500 words chatGPT and Claude generated over 9000 words. could it be a prompt issue" [X Link](https://x.com/joestackss/status/1980229039785910724) [@joestackss](/creator/x/joestackss) 2025-10-20T11:06Z 12.8K followers, 1384 engagements "Machine Learning Explained: A Guide to ML AI & Deep Learning" [YouTube Link](https://youtube.com/watch?v=znF2U_3Z210) [@ibmtechnology](/creator/youtube/ibmtechnology) 2025-10-20T11:01Z 1.4M followers, 1245 engagements "it's weird how people are so anxious for the Gemini X release but it also makes me wonder what this new model will do for the end users that the current Gemini XXX pro doesn't for most people it won't meaningfully change their use cases even the best LLMs still make things up sometimes" [X Link](https://x.com/slow_developer/status/1980222562702401892) [@slow_developer](/creator/x/slow_developer) 2025-10-20T10:40Z 51.9K followers, 2710 engagements
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
Showing only X posts for non-authenticated requests. Use your API key in requests for full results.
"🚀 DeepSeek-OCR the new frontier of OCR from @deepseek_ai exploring optical context compression for LLMs is running blazingly fast on vLLM ⚡ (2500 tokens/s on A100-40G) powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to XX while keeping XX% OCR accuracy at XX. 📄 Outperforms GOT-OCR2.0 & MinerU2.0 on OmniDocBench using fewer vision tokens. 🤝 The vLLM team is working with DeepSeek to bring official DeepSeek-OCR support into the next vLLM release making multimodal inference even faster and easier to scale. 🔗 #vLLM #DeepSeek #OCR #LLM #VisionAI #DeepLearning"
X Link @vllm_project 2025-10-20T11:31Z 19.9K followers, 3311 engagements
"most LLMs have problem with word count. I asked for 2500 words chatGPT and Claude generated over 9000 words. could it be a prompt issue"
X Link @joestackss 2025-10-20T11:06Z 12.8K followers, 1384 engagements
"Machine Learning Explained: A Guide to ML AI & Deep Learning"
YouTube Link @ibmtechnology 2025-10-20T11:01Z 1.4M followers, 1245 engagements
"it's weird how people are so anxious for the Gemini X release but it also makes me wonder what this new model will do for the end users that the current Gemini XXX pro doesn't for most people it won't meaningfully change their use cases even the best LLMs still make things up sometimes"
X Link @slow_developer 2025-10-20T10:40Z 51.9K followers, 2710 engagements
/topic/llms/posts