Top Tweets for #BentoFriday

over 1 year ago

#BentoFriday 🍱 — Add a Web UI with @Gradio Real-world #AI apps don’t just need a model. They need interfaces users can interact with. But building a custom frontend is time-consuming and managing it separately from your backend adds unnecessary complexity. 😵‍💫 With #BentoML, you can mount a #Gradio UI directly into your AI service — all in Python. ✅ Build a slick web UI with Gradio ✅ Connect it to a scalable backend powered by BentoML ✅ Serve both APIs and UI in one deployment ✅ Efficient #LLM inference, multi-model pipelines, async queues and adaptive batching ✅ Auto-package into a Docker image with built-in metrics and health checks ✅ Deploy to #BentoCloud with optimized model loading and fast autoscaling 📚 Docs: https://t.co/aH00sEPf7o Here’s what it looks like 👇

bentomlai's tweet photo. #BentoFriday 🍱 — Add a Web UI with @Gradio

Real-world #AI apps don’t just need a model. They need interfaces users can interact with.

But building a custom frontend is time-consuming and managing it separately from your backend adds unnecessary complexity. 😵‍💫

With #BentoML, you can mount a #Gradio UI directly into your AI service — all in Python.
✅ Build a slick web UI with Gradio
✅ Connect it to a scalable backend powered by BentoML
✅ Serve both APIs and UI in one deployment
✅ Efficient #LLM inference, multi-model pipelines, async queues and adaptive batching
✅ Auto-package into a Docker image with built-in metrics and health checks
✅ Deploy to #BentoCloud with optimized model loading and fast autoscaling

📚 Docs: https://t.co/aH00sEPf7o

Here’s what it looks like 👇

0

7

3

820

over 1 year ago

#BentoFriday 🍱 — Runtime Specs in Pure Python Deploying #AI services isn’t just about your model code; it’s also about getting the right runtime and making sure it is reproducible across environments. That might include: 🐍 Python version 🖥️ OS & system packages 📦 Python dependencies ⚙️ Custom build commands and scripts Without a standard approach, it can get messy and painful. 😩 #BentoML fixes that with its standard #Python SDK: ✅ Define everything in pure Python ✅ Support for PyPI, custom wheels, GitHub packages, private repos, and more ✅ Run custom commands and scripts in the build process ✅ Avoid unnecessary rebuilds with smart caching ✅ Automatic packaging, containerization and deployment 📚 Dive deeper: https://t.co/pgs7WfAKF1 Here’s what it looks like in code ⬇️ #MLOps #AIInfrastructure #MachineLearning #LLMInference

bentomlai's tweet photo. #BentoFriday 🍱 — Runtime Specs in Pure Python

Deploying #AI services isn’t just about your model code; it’s also about getting the right runtime and making sure it is reproducible across environments. That might include:

🐍 Python version
🖥️ OS & system packages
📦 Python dependencies
⚙️ Custom build commands and scripts

Without a standard approach, it can get messy and painful. 😩

#BentoML fixes that with its standard #Python SDK:
✅ Define everything in pure Python
✅ Support for PyPI, custom wheels, GitHub packages, private repos, and more
✅ Run custom commands and scripts in the build process
✅ Avoid unnecessary rebuilds with smart caching
✅ Automatic packaging, containerization and deployment

📚 Dive deeper: https://t.co/pgs7WfAKF1

Here’s what it looks like in code ⬇️
#MLOps #AIInfrastructure #MachineLearning #LLMInference

0

2

0

183

over 1 year ago

#BentoFriday 🍱 — Inference Context with 𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘊𝘰𝘯𝘵𝘦𝘹𝘵 Building #AI/ML APIs isn’t just about calling a model. You need a clean, reliable way to customize your inference service. 𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘊𝘰𝘯𝘵𝘦𝘹𝘵 is one of those abstractions in #BentoML that gives the control you need: ✅ Access request headers ✅ Set response headers, cookies, or status codes ✅ Use a temp directory 𝘤𝘵𝘹.𝘵𝘦𝘮𝘱_𝘥𝘪𝘳 to write files ✅ Track per-worker state with 𝘤𝘵𝘹.𝘴𝘵𝘢𝘵𝘦 All that while keeping your logic clean and readable. Here’s an example serving the FLUX.1-schnell model, logging metadata, customizing the response, and saving the generated image 👇 📖 Learn more: https://t.co/xCVImahnC5

bentomlai's tweet photo. #BentoFriday 🍱 — Inference Context with 𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘊𝘰𝘯𝘵𝘦𝘹𝘵

Building #AI/ML APIs isn’t just about calling a model. You need a clean, reliable way to customize your inference service.

𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘊𝘰𝘯𝘵𝘦𝘹𝘵 is one of those abstractions in #BentoML that gives the control you need:
✅ Access request headers
✅ Set response headers, cookies, or status codes
✅ Use a temp directory 𝘤𝘵𝘹.𝘵𝘦𝘮𝘱_𝘥𝘪𝘳 to write files
✅ Track per-worker state with 𝘤𝘵𝘹.𝘴𝘵𝘢𝘵𝘦

All that while keeping your logic clean and readable.

Here’s an example serving the FLUX.1-schnell model, logging metadata, customizing the response, and saving the generated image 👇

📖 Learn more: https://t.co/xCVImahnC5

0

5

0

2

295

over 1 year ago

#BentoFriday 🍱 — Lifecycle Hooks in #BentoML When deploying real-world #AI services, the work doesn’t end at inference. You also need to manage everything that happens before, during, and after a request hits your model. In practice, that often means: 🔧 Setting up global resources at startup 📚 Loading databases or caches 🩺 Checking service health and readiness 🧹 Releasing memory and cleaning up connections Without a clean structure, you may end up with messy boilerplate, missed init logic, painful resource leaks, and hard-to-trace bugs. ⏳ 𝗪𝗵𝗮𝘁'𝘀 𝘄𝗼𝗿𝘀𝗲, 𝗶𝘁 𝘁𝗮𝗸𝗲𝘀 𝘁𝗶𝗺𝗲 𝘁𝗼 𝗴𝗲𝘁 𝗿𝗶𝗴𝗵𝘁. That’s why BentoML makes it simple with lifecycle hooks. Just add a few decorators: ✅ @𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘰𝘯_𝘥𝘦𝘱𝘭𝘰𝘺𝘮𝘦𝘯𝘵: One-time setup before spawning workers ✅ @𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘰𝘯_𝘴𝘵𝘢𝘳𝘵𝘶𝘱: Per-worker initialization (sync/async supported) ✅ @𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘰𝘯_𝘴𝘩𝘶𝘵𝘥𝘰𝘸𝘯: Graceful cleanup during shutdown ✅ __𝘪𝘴_𝘢𝘭𝘪𝘷𝘦__ & __𝘪𝘴_𝘳𝘦𝘢𝘥𝘺__: Health & readiness checks for /𝘭𝘪𝘷𝘦𝘻 and /𝘳𝘦𝘢𝘥𝘺𝘻 Build cleaner and safer AI services with just a few lines of code. Learn more: https://t.co/G9epaMU101 Here’s a simple example:

bentomlai's tweet photo. #BentoFriday 🍱 — Lifecycle Hooks in #BentoML

When deploying real-world #AI services, the work doesn’t end at inference. You also need to manage everything that happens before, during, and after a request hits your model.

In practice, that often means:
🔧 Setting up global resources at startup
📚 Loading databases or caches
🩺 Checking service health and readiness
🧹 Releasing memory and cleaning up connections

Without a clean structure, you may end up with messy boilerplate, missed init logic, painful resource leaks, and hard-to-trace bugs. ⏳ 𝗪𝗵𝗮𝘁'𝘀 𝘄𝗼𝗿𝘀𝗲, 𝗶𝘁 𝘁𝗮𝗸𝗲𝘀 𝘁𝗶𝗺𝗲 𝘁𝗼 𝗴𝗲𝘁 𝗿𝗶𝗴𝗵𝘁.

That’s why BentoML makes it simple with lifecycle hooks. Just add a few decorators:
✅ @𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘰𝘯_𝘥𝘦𝘱𝘭𝘰𝘺𝘮𝘦𝘯𝘵: One-time setup before spawning workers
✅ @𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘰𝘯_𝘴𝘵𝘢𝘳𝘵𝘶𝘱: Per-worker initialization (sync/async supported)
✅ @𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘰𝘯_𝘴𝘩𝘶𝘵𝘥𝘰𝘸𝘯: Graceful cleanup during shutdown
✅ __𝘪𝘴_𝘢𝘭𝘪𝘷𝘦__ & __𝘪𝘴_𝘳𝘦𝘢𝘥𝘺__: Health & readiness checks for /𝘭𝘪𝘷𝘦𝘻 and /𝘳𝘦𝘢𝘥𝘺𝘻

Build cleaner and safer AI services with just a few lines of code. Learn more: https://t.co/G9epaMU101

Here’s a simple example:

0

2

0

1

147

over 1 year ago

#BentoFriday 🍱 — Distributed Services in #BentoML #AI deployments are going distributed. Some examples: 🔧 Disaggregated #LLM serving 🔍 KV-aware LLM routing 🧠 Multi-model Computer Vision pipelines 🔐 LLM safety & moderation layers 🔁 #RAG pipelines In these systems, components are tidily coupled. Running them all on a single node (heterogeneous CPU/GPU/IO compute) often leads to compute waste and reduced throughput. To optimize compute utilization and latency, you often want to break them into individual components, leading to complex micro-services architecture. What if you could develop such distributed application all in one Python file, and easily orchestrate it across distributed infrastructure for evaluation and deployment? That’s what 𝗕𝗲𝗻𝘁𝗼𝗠𝗟 𝗗𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗲𝗱 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝘀 are built for: ✅ Use 𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘥𝘦𝘱𝘦𝘯𝘥𝘴() to wire them together ✅ Each component with their own environment, scaling strategy, models and hardware specifications (CPU/GPU) ✅ Call dependent service APIs as if they were local Python functions ✅ Automatic service discovery & routing ✅ Simplified control over concurrency, throughput, and resource utilization 📚 Learn more: https://t.co/0lYza2E1sq

bentomlai's tweet photo. #BentoFriday 🍱 — Distributed Services in #BentoML

#AI deployments are going distributed. Some examples:
🔧 Disaggregated #LLM serving
🔍 KV-aware LLM routing
🧠 Multi-model Computer Vision pipelines
🔐 LLM safety & moderation layers
🔁 #RAG pipelines

In these systems, components are tidily coupled. Running them all on a single node (heterogeneous CPU/GPU/IO compute) often leads to compute waste and reduced throughput. To optimize compute utilization and latency, you often want to break them into individual components, leading to complex micro-services architecture.

What if you could develop such distributed application all in one Python file, and easily orchestrate it across distributed infrastructure for evaluation and deployment?

That’s what 𝗕𝗲𝗻𝘁𝗼𝗠𝗟 𝗗𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗲𝗱 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝘀 are built for:
✅ Use 𝘣𝘦𝘯𝘵𝘰𝘮𝘭.𝘥𝘦𝘱𝘦𝘯𝘥𝘴() to wire them together
✅ Each component with their own environment, scaling strategy, models and hardware specifications (CPU/GPU)
✅ Call dependent service APIs as if they were local Python functions
✅ Automatic service discovery & routing
✅ Simplified control over concurrency, throughput, and resource utilization

📚 Learn more: https://t.co/0lYza2E1sq

0

3

0

1

256

over 1 year ago

#BentoFriday 🍱 — BentoCloud Unified Inference Platform Developers love #BentoML for its ease of building scalable #AI inference services and distributed real-time AI applications. With #BentoCloud, we are taking this vision of simplifying AI inference operations further to enterprises. Learn how you can one-click deploy #Llama4 to your AWS/GCP account via BentoCloud, and unlock the path to advanced inference setups and customizations: 🍱 Various pre-built #Bentos with the latest models like Llama 4 ⌨️ Custom APIs, inference setups, business logic, and more 🔁 Autoscaling with fast cold starts & scale-to-zero 📊 Real-time logs & dashboards for full observability 🔒 Full control with Bring Your Own Cloud (#BYOC) and on-prem support …and many more! #OpenSource #BentoML #BentoCloud #MachineLearning

0

6

0

2

240

over 1 year ago

#BentoFriday 🍱 — Adaptive Batching When building online #ML services with a web #API serving stack, you're often limited to processing one request at a time. But do you know — Your #AI/ML model and its runtime are highly optimized for parallelism. They can process batches of inputs with only marginal compute overhead compared to making one prediction. 🤔 A naive fix? Wait for a fixed batch size or timeout before processing? ❌ That adds latency and it’s not ideal for real-time apps. That’s where 🍱 #BentoML’s adaptive batching comes in: ✅ Just set `batchable=True` on your API ✅ Dynamically group multiple requests ✅ Adjust batch size & window based on real-time traffic ✅ Higher throughput & lower latency 📚 Dive deeper: https://t.co/IRFSQhwVzs

bentomlai's tweet photo. #BentoFriday 🍱 — Adaptive Batching

When building online #ML services with a web #API serving stack, you're often limited to processing one request at a time.

But do you know — Your #AI/ML model and its runtime are highly optimized for parallelism. They can process batches of inputs with only marginal compute overhead compared to making one prediction.

🤔 A naive fix? Wait for a fixed batch size or timeout before processing? ❌ That adds latency and it’s not ideal for real-time apps.

That’s where 🍱 #BentoML’s adaptive batching comes in:
✅ Just set `batchable=True` on your API
✅ Dynamically group multiple requests
✅ Adjust batch size & window based on real-time traffic
✅ Higher throughput & lower latency

📚 Dive deeper: https://t.co/IRFSQhwVzs

0

5

0

1

218

about 6 years ago

Halloween bento for my preschool grandson. I make a bento every Friday to encourage him to eat. String cheese fingers, spider deviled egg, tangerine Jack-o-lantern. #bento #Halloween #kidslunchideas #bentofriday #おべんと　#子供のお弁当

Grandmasday's tweet photo. Halloween bento for my preschool grandson. I make a bento every Friday to encourage him to eat. String cheese fingers, spider deviled egg, tangerine Jack-o-lantern. #bento #Halloween #kidslunchideas #bentofriday #おべんと　#子供のお弁当 https://t.co/NR7BcjnohI

0

2

0

about 6 years ago

Every Friday, a new idea for a child’s bento lunch. #bentofriday #bentolunch #grandmalove #おべんと　#子供のお弁当

about 6 years ago

So caught up in the news, I forgot to post today’s bento. Child-size burger on homemade sourdough bun, Goldfish, avocado & peach balls, strawberries. #bento #bentofriday #schoollunch #brownbag #burger #EyesHaveIt

Grandmasday's tweet photo. So caught up in the news, I forgot to post today’s bento. Child-size burger on homemade sourdough bun, Goldfish, avocado & peach balls, strawberries. #bento #bentofriday #schoollunch #brownbag #burger #EyesHaveIt https://t.co/yCNncQ2rr3

0

1

0

3

0

about 6 years ago

Today’s bento for Little N. Cold somen noodles with dipping sauce, deviled eggs, cherry tomatoes, dried blueberries, and orange segments. #bento #kidsbento #bentobox #brownbag #grandmalove #schoollunch #bentofriday #somen #tomatoes #blueberries #oranges #deviledeggs

Grandmasday's tweet photo. Today’s bento for Little N. Cold somen noodles with dipping sauce, deviled eggs, cherry tomatoes, dried blueberries, and orange segments.
#bento #kidsbento #bentobox #brownbag #grandmalove #schoollunch #bentofriday #somen #tomatoes #blueberries #oranges #deviledeggs https://t.co/RN9d4aAzGU

0

2

0

about 6 years ago

Little N’s bento today. Bullet train onigiri, broccoli, rolled omelet with nori, and orange sections. #bento #kidsbento #bentobox #schoollunch #brownbag #grandmalove #bento #onigiri #nori #bentofriday #backtoschool #おべんとう #子供のお弁当 #おにぎり

Grandmasday's tweet photo. Little N’s bento today. Bullet train onigiri, broccoli, rolled omelet with nori, and orange sections. #bento #kidsbento #bentobox #schoollunch #brownbag #grandmalove #bento #onigiri #nori #bentofriday #backtoschool #おべんとう #子供のお弁当 #おにぎり https://t.co/i2qNbKM81i

0

5

0

about 6 years ago

Bento for Little N: bear & bunny pizzas w/Cheddar and apple, avocado with Parmigiano Reggiano (his idea), grapes, and carrots. . #bento #kidsbento #schoollunch #brownbag #bento #bentofriday #backtoschool #pizza #cheddar #apple #avocado #grapes #carrots #おべんとう #子供のお弁当

Grandmasday's tweet photo. Bento for Little N: bear & bunny pizzas w/Cheddar and apple, avocado with Parmigiano Reggiano (his idea), grapes, and carrots. .
#bento #kidsbento #schoollunch #brownbag #bento #bentofriday #backtoschool #pizza #cheddar #apple #avocado #grapes #carrots #おべんとう #子供のお弁当 https://t.co/TmNKav87nX

1

4

0

almost 8 years ago

Today’s bento for Mis T: bacon-wrapped dried plums, Dubliner panini soldiers with avocado smush for dipping, tomatoes and homemade Valentine cookies. #bento #bentofriday #driedplums #dublinercheese #valentine

specialforksndy's tweet photo. Today’s bento for Mis T: bacon-wrapped dried plums, Dubliner panini soldiers with avocado smush for dipping, tomatoes and homemade Valentine cookies. #bento #bentofriday #driedplums #dublinercheese #valentine https://t.co/oS0dL1bqL8

0

2

0

about 8 years ago

Halloween bento: string cheese fingers, salami cones, deviled egg spiders and clementine jack-o-lantern. #bento #bentofriday #halloween #halloweenbento #specialforkbento #kidsbento #schoollunch #lunchbox #lunchboxideas #brownbaglunch #obento #yummy #べんとう #オベントウ

specialforksndy's tweet photo. Halloween bento: string cheese fingers, salami cones, deviled egg spiders and clementine jack-o-lantern. #bento #bentofriday #halloween #halloweenbento #specialforkbento #kidsbento #schoollunch #lunchbox #lunchboxideas #brownbaglunch #obento #yummy #べんとう #オベントウ https://t.co/OhMSpUXOjI

1

2

0

about 8 years ago

Miss T’s bento: manchego panini in leaf shapes, apple, artichoke & choc strawberries. #manchego #panini #artichoke #strawberries #bento #lunchbox #bentofriday #schoollunch #bentolunch #lunchboxideas #brownbaglunch #obento #grandmalove #yummy #huffposttaste #べんとう #オベント

specialforksndy's tweet photo. Miss T’s bento: manchego panini in leaf shapes, apple, artichoke & choc strawberries. #manchego #panini #artichoke #strawberries #bento #lunchbox #bentofriday #schoollunch #bentolunch #lunchboxideas #brownbaglunch #obento #grandmalove #yummy #huffposttaste #べんとう #オベント https://t.co/lIOExX1Qig

2

6

3

0

over 8 years ago

Miss T’s bento: cold somen noodles with sauce in fish bottle, tomatoes, apple wedges, Japanese omelet rolled with nori. #bento #bentofriday #somen #omelet #nori #べんという #おbんとう

specialforksndy's tweet photo. Miss T’s bento: cold somen noodles with sauce in fish bottle, tomatoes, apple wedges, Japanese omelet rolled with nori. #bento #bentofriday #somen #omelet #nori #べんという #おbんとう https://t.co/q0iXAp6QJ0

3

6

0

over 8 years ago

Today’s bento for Little Miss T: mini omelets with diced potatoes, unicorn toasts, broccoli, Skellig Cheese hearts, and strawberries. . . . . #unicorn #toast #eggs #omelet #skelligcheese #broccoli #strawberries #bento #bentofriday #specialforkbento #kidsbento #schoollunch #k…

specialforksndy's tweet photo. Today’s bento for Little Miss T: mini omelets with diced potatoes, unicorn toasts, broccoli, Skellig Cheese hearts, and strawberries. .
.
.
.
#unicorn #toast #eggs #omelet #skelligcheese #broccoli #strawberries #bento #bentofriday #specialforkbento #kidsbento #schoollunch #k… https://t.co/x0akaNYgKp

2

7

1

0

over 8 years ago

Miss T’s bento today: somen noodles with dipping sauce (in honey bear) and cherry blossom carrots, broccoli with oyster sauce, and three little sausage people. . . . . #bento #bentofriday #somen #carrots #broccoli #specialforkbento #kidsbento #rilakkuma #lunchbox #brownbaglu…

specialforksndy's tweet photo. Miss T’s bento today: somen noodles with dipping sauce (in honey bear) and cherry blossom carrots, broccoli with oyster sauce, and three little sausage people.
.
.
.
.
#bento #bentofriday #somen #carrots #broccoli #specialforkbento #kidsbento #rilakkuma #lunchbox #brownbaglu… https://t.co/SvU2H9kD5Q

2

7

2

0