Why serving architecture affects latency and cost in MLOps - See It in Action

Why Serving Architecture Affects Latency and Cost

📖 Scenario: You work in a team that deploys machine learning models to serve predictions to users. Your team wants to understand how different serving architectures impact the speed of responses (latency) and the money spent (cost).Imagine you have two ways to serve a model: one that handles requests one by one (simple server), and another that batches requests together to save resources.

🎯 Goal: Build a simple Python simulation that models request handling in two serving architectures. You will create data for requests, configure batch size, apply logic to simulate processing time, and output the average latency and estimated cost for each architecture.

📋 What You'll Learn

Create a list of exactly 10 request processing times in milliseconds

Add a configuration variable called batch_size with value 3

Write code to calculate average latency for simple and batch serving

Print the average latency and estimated cost for both architectures

💡 Why This Matters

🌍 Real World

In real machine learning deployments, choosing how to serve models affects how fast users get predictions and how much cloud resources cost.

💼 Career

Understanding serving architectures helps DevOps and MLOps engineers optimize performance and budget in production systems.

1

Create request processing times list

Create a list called request_times with these exact values in milliseconds: [120, 150, 100, 130, 110, 140, 115, 125, 135, 105]

MLOps

# Create the request_times list with given values
# Your code here

Hint

Use square brackets and separate numbers with commas exactly as shown.

2

Add batch size configuration

Add a variable called batch_size and set it to 3

MLOps

request_times = [120, 150, 100, 130, 110, 140, 115, 125, 135, 105]
# Set batch_size to 3
# Your code here

Hint

Just assign the number 3 to the variable named batch_size.

3

Calculate average latency for simple and batch serving

Write code to calculate simple_avg_latency as the average of all request_times, and batch_avg_latency by grouping request_times into batches of size batch_size, taking the maximum time in each batch as batch processing time, then averaging these batch times.

MLOps

request_times = [120, 150, 100, 130, 110, 140, 115, 125, 135, 105]
batch_size = 3
# Calculate simple_avg_latency and batch_avg_latency
# Your code here

Hint

Use list slicing and max() to find batch times, then average them.

4

Print average latency and estimated cost

Print the average latency for simple serving as Simple Avg Latency: X ms and for batch serving as Batch Avg Latency: Y ms. Then print estimated cost assuming simple serving costs $0.10 per request and batch serving costs $0.25 per batch, formatted as Simple Cost: $Z and Batch Cost: $W. Use two decimal places for costs.

MLOps

request_times = [120, 150, 100, 130, 110, 140, 115, 125, 135, 105]
batch_size = 3
simple_avg_latency = sum(request_times) / len(request_times)
batches = [request_times[i:i+batch_size] for i in range(0, len(request_times), batch_size)]
batch_times = [max(batch) for batch in batches]
batch_avg_latency = sum(batch_times) / len(batch_times)
# Print average latencies and costs
# Your code here

Hint

Calculate costs by multiplying per-request or per-batch rates. Use f-strings to format output.

Practice

1. Which serving architecture typically offers the lowest latency for model predictions?

easy

A. Offline serving

B. Batch serving

C. Edge serving

D. Cloud batch processing

Solution

1. Step 1: Understand latency in serving architectures

   Latency means the delay before a prediction is returned. Edge serving places the model close to the user, reducing delay.

2. Step 2: Compare architectures

   Batch serving processes data in groups and is slower. Edge serving is designed for fast responses near the user.

3. Final Answer:

   Edge serving -> Option C

4. Quick Check:

   Lowest latency = Edge serving [OK]

Hint: Edge serving is closest to users, so fastest response [OK]

Common Mistakes:

• Confusing batch serving as low latency
• Thinking cloud batch is fastest
• Ignoring edge location benefits

2. Which statement correctly describes batch serving in ML model deployment?

easy

A. Batch serving provides real-time predictions with high cost.

B. Batch serving processes data in groups and is usually cheaper but slower.

C. Batch serving always runs on edge devices.

D. Batch serving requires no compute resources.

Solution

1. Step 1: Define batch serving

   Batch serving processes multiple data points together, not one by one, which saves cost but adds delay.

2. Step 2: Evaluate options

   Batch serving processes data in groups and is usually cheaper but slower. correctly states batch serving is cheaper but slower. Other options are incorrect or unrealistic.

3. Final Answer:

   Batch serving processes data in groups and is usually cheaper but slower. -> Option B

4. Quick Check:

   Batch serving = cheaper, slower [OK]

Hint: Batch = groups, cheaper but slower [OK]

Common Mistakes:

• Thinking batch serving is real-time
• Assuming batch runs on edge devices
• Believing batch needs no compute

3. Given a model deployed with online serving and another with batch serving, which output best describes their latency and cost?

medium

A. Online serving: low latency, high cost; Batch serving: high latency, low cost

B. Online serving: high latency, low cost; Batch serving: low latency, high cost

C. Both have similar latency and cost

D. Online serving is always cheaper than batch serving

Solution

1. Step 1: Recall characteristics of online and batch serving

   Online serving provides predictions immediately (low latency) but requires more resources (high cost). Batch serving delays predictions but is cheaper.

2. Step 2: Match options to characteristics

   Online serving: low latency, high cost; Batch serving: high latency, low cost correctly matches low latency and high cost to online serving, and high latency and low cost to batch serving.

3. Final Answer:

   Online serving: low latency, high cost; Batch serving: high latency, low cost -> Option A

4. Quick Check:

   Online = fast & costly, Batch = slow & cheap [OK]

Hint: Online = fast+costly, Batch = slow+cheap [OK]

Common Mistakes:

• Swapping latency and cost roles
• Assuming both have same cost
• Thinking batch is faster

4. A team deployed a model using edge serving but notices high latency and cost. What is the most likely cause?

medium

A. Edge serving always causes high latency and cost

B. Batch processing was mistakenly used instead of edge serving

C. The model is deployed in a cloud data center far from users

D. The model is too large to run efficiently on edge devices

Solution

1. Step 1: Understand edge serving constraints

   Edge devices have limited resources. Large models can slow down processing and increase cost.

2. Step 2: Analyze options

   The model is too large to run efficiently on edge devices explains the likely cause. Batch processing was mistakenly used instead of edge serving is incorrect because batch serving is different. The model is deployed in a cloud data center far from users describes cloud serving, not edge. Edge serving always causes high latency and cost is false.

3. Final Answer:

   The model is too large to run efficiently on edge devices -> Option D

4. Quick Check:

   Large model on edge = high latency/cost [OK]

Hint: Large models slow edge devices, raising latency and cost [OK]

Common Mistakes:

• Confusing edge with cloud serving
• Assuming edge always has high latency
• Mixing batch and edge serving

5. A company wants to minimize prediction latency for users worldwide but has a limited budget. Which serving architecture balances latency and cost best?

hard

A. Combine edge serving for critical regions and batch serving elsewhere

B. Deploy models only in a central cloud data center

C. Use batch serving exclusively for all predictions

D. Deploy large models on every user device

Solution

1. Step 1: Analyze latency and cost trade-offs

   Central cloud has higher latency for distant users. Batch serving is cheap but slow. Edge serving is fast but costly.

2. Step 2: Evaluate hybrid approach

   Combining edge serving in key regions reduces latency where needed, while batch serving elsewhere controls costs.

3. Final Answer:

   Combine edge serving for critical regions and batch serving elsewhere -> Option A

4. Quick Check:

   Hybrid edge + batch balances latency and cost [OK]

Hint: Hybrid edge and batch serving balances speed and cost [OK]

Common Mistakes:

• Choosing only cloud causing high latency
• Using batch only causing slow responses
• Deploying large models on all devices is costly