#mloptimization — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #mloptimization, aggregated by home.social.
-
Việc đặt tiêu đề cho ~50k ảnh/ngày cần GPU mạnh. Kinh nghiệm cho các mô hình VLM như uform-gen2-qwen-500m hoặc qwen2.5-vl:7b. Đề xuất GPU L40, AWS G5 để tối ưu tốc độ và chi phí. #GPU #AI_vi #DeepLearning #CaptionGenerator #MLOptimization
-
Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
https://arxiv.org/abs/2508.12631
#HackerNews #Making #LLMs #Cheaper #and #Better #via #Performance-Efficiency #Optimized #Routing
LLMs #PerformanceEfficiency #AIResearch #MLOptimization #CostReduction
-
Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
https://arxiv.org/abs/2508.12631
#HackerNews #Making #LLMs #Cheaper #and #Better #via #Performance-Efficiency #Optimized #Routing
LLMs #PerformanceEfficiency #AIResearch #MLOptimization #CostReduction
-
Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
https://arxiv.org/abs/2508.12631
#HackerNews #Making #LLMs #Cheaper #and #Better #via #Performance-Efficiency #Optimized #Routing
LLMs #PerformanceEfficiency #AIResearch #MLOptimization #CostReduction
-
Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
https://arxiv.org/abs/2508.12631
#HackerNews #Making #LLMs #Cheaper #and #Better #via #Performance-Efficiency #Optimized #Routing
LLMs #PerformanceEfficiency #AIResearch #MLOptimization #CostReduction
-
Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
https://arxiv.org/abs/2508.12631
#HackerNews #Making #LLMs #Cheaper #and #Better #via #Performance-Efficiency #Optimized #Routing
LLMs #PerformanceEfficiency #AIResearch #MLOptimization #CostReduction
-
MLP Accelerators are Changing TinyML for Edge Computing
https://rackenzik.com/how-mlp-accelerators-are-changing-tinyml-for-edge-computing/
#TinyML #EdgeAI #MLPAccelerators #FPGAs #EmbeddedAI #AIOnTheEdge #LowPowerAI #MachineLearning #EdgeComputing #AIHardware #AIInnovation #SmartDevices #OnDeviceAI #MLOptimization #TechForGood
-
MLP Accelerators are Changing TinyML for Edge Computing
https://rackenzik.com/how-mlp-accelerators-are-changing-tinyml-for-edge-computing/
#TinyML #EdgeAI #MLPAccelerators #FPGAs #EmbeddedAI #AIOnTheEdge #LowPowerAI #MachineLearning #EdgeComputing #AIHardware #AIInnovation #SmartDevices #OnDeviceAI #MLOptimization #TechForGood
-
🎩🤖 "Metagradient Descent" promises the magic of optimizing ML, but is more like watching paint dry at warp speed. 📉👏 With support from the mystical Simons Foundation, we now have another wizardry paper that's essentially just trying to make gradients great again. 🧙♂️✨
https://arxiv.org/abs/2503.13751 #MetagradientDescent #MLoptimization #SimonsFoundation #AIresearch #GradientMagic #HackerNews #ngated -
🎩🤖 "Metagradient Descent" promises the magic of optimizing ML, but is more like watching paint dry at warp speed. 📉👏 With support from the mystical Simons Foundation, we now have another wizardry paper that's essentially just trying to make gradients great again. 🧙♂️✨
https://arxiv.org/abs/2503.13751 #MetagradientDescent #MLoptimization #SimonsFoundation #AIresearch #GradientMagic #HackerNews #ngated -
🎩🤖 "Metagradient Descent" promises the magic of optimizing ML, but is more like watching paint dry at warp speed. 📉👏 With support from the mystical Simons Foundation, we now have another wizardry paper that's essentially just trying to make gradients great again. 🧙♂️✨
https://arxiv.org/abs/2503.13751 #MetagradientDescent #MLoptimization #SimonsFoundation #AIresearch #GradientMagic #HackerNews #ngated -
🎩🤖 "Metagradient Descent" promises the magic of optimizing ML, but is more like watching paint dry at warp speed. 📉👏 With support from the mystical Simons Foundation, we now have another wizardry paper that's essentially just trying to make gradients great again. 🧙♂️✨
https://arxiv.org/abs/2503.13751 #MetagradientDescent #MLoptimization #SimonsFoundation #AIresearch #GradientMagic #HackerNews #ngated