Skip to main content

What is the Impact of Quantisation on Memory Utilisation

 

AspectImpact on Memory Utilization
Large Language Models (LLMs)Reduced Model Size: Quantization reduces the number of bits used to represent each weight and activation. For example, converting from 32-bit floating point (FP32) to 8-bit integer (INT8) reduces memory usage by a factor of 4.

Lower Memory Footprint: This reduction in precision leads to a lower overall memory footprint for storing the model parameters and intermediate activations during inference and training. 

Increased Batch Sizes: With lower memory requirements, it becomes possible to process larger batch sizes within the same memory constraints, improving throughput.
Vector DatabasesCompact Embeddings: Quantization reduces the size of vector embeddings stored in the database. For instance, converting vectors from 32-bit to 8-bit representation decreases storage requirements by up to 75%. 

Efficient Indexing: Smaller vector sizes allow for more efficient indexing and faster retrieval operations due to reduced memory bandwidth and cache usage. 

Scalability: The reduction in memory usage enables the handling of larger datasets and more vectors within the same hardware constraints, improving the scalability of the system.

Benefits of Reduced Memory Utilization

  • Cost Efficiency: Lower memory usage translates to reduced hardware costs, as less RAM and storage are required.
  • Energy Efficiency: Less memory usage often results in lower power consumption, contributing to energy efficiency.
  • Performance Improvements: Reduced memory usage can lead to faster data access and processing times, as more data can fit into the faster levels of the memory hierarchy (e.g., caches).
  • Deployment Flexibility: Models and databases with lower memory footprints can be deployed on a wider range of devices, including edge devices with limited resources.
Labels:

Comments

Post a Comment

Popular posts from this blog

What is the difference between Elastic and Enterprise Redis w.r.t "Hybrid Query" capabilities

  We'll explore scenarios involving nested queries, aggregations, custom scoring, and hybrid queries that combine multiple search criteria. 1. Nested Queries ElasticSearch Example: ElasticSearch supports nested documents, which allows for querying on nested fields with complex conditions. Query: Find products where the product has a review with a rating of 5 and the review text contains "excellent". { "query": { "nested": { "path": "reviews", "query": { "bool": { "must": [ { "match": { "reviews.rating": 5 } }, { "match": { "reviews.text": "excellent" } } ] } } } } } Redis Limitation: Redis does not support nested documents natively. While you can store nested structures in JSON documents using the RedisJSON module, querying these nested structures with complex condi...
Post a Comment
Read more

Error: could not find function "read.xlsx" while reading .xlsx file in R

Got this during the execution of following command in R > dat Error: could not find function "read.xlsx" Tried following command > install.packages("xlsx", dependencies = TRUE) Installing package into ‘C:/Users/amajumde/Documents/R/win-library/3.2’ (as ‘lib’ is unspecified) also installing the dependencies ‘rJava’, ‘xlsxjars’ trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/rJava_0.9-8.zip' Content type 'application/zip' length 766972 bytes (748 KB) downloaded 748 KB trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/xlsxjars_0.6.1.zip' Content type 'application/zip' length 9485170 bytes (9.0 MB) downloaded 9.0 MB trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/xlsx_0.5.7.zip' Content type 'application/zip' length 400968 bytes (391 KB) downloaded 391 KB package ‘rJava’ successfully unpacked and MD5 sums checked package ‘xlsxjars’ successfully unpacked ...
Post a Comment
Read more

Training LLM model requires more GPU RAM than storing same LLM

Storing an LLM model and training the same model both require memory, but the memory requirements for training are typically higher than just storing the model. Let's dive into the details: Memory Requirement for Storing the Model: When you store an LLM model, you need to save the weights of the model parameters. Each parameter is typically represented by a 32-bit float (4 bytes). The memory requirement for storing the model weights is calculated by multiplying the number of parameters by 4 bytes. For example, if you have a model with 1 billion parameters, the memory requirement for storing the model weights alone would be 4 GB (4 bytes * 1 billion parameters). Memory Requirement for Training: During the training process, additional components use GPU memory in addition to the model weights. These components include optimizer states, gradients, activations, and temporary variables needed by the training process. These components can require additional memory beyond just storing th...
Post a Comment
Read more