Skip to content

Latest commit

 

History

History

bench_deepspeed

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

DeepSpeed

GitHub Repo  

DeepSpeed by Microsoft is a library that helps us to do scalable training and inference across multiple GPUs and nodes. In this implementation we are using a library called DeepSpeed-MII, written on top of DeepSpeed. It uses four key technologies to speed up the inference, viz Blocked KV Caching, Continuous Batching, Dynamic SplitFuse and High Performance CUDA Kernels. To learn more about DeepSpeed-MII, check out there detailed blogpost.

🚀 Running the DeepSpeed Benchmark.

We can run the DeepSpeed benchmark for two models: Llama2 7B Chat and Mistral-7B v0.1 Instruct Here is how we run benchmark for DeepSpeed.

./bench_deepspeed/bench.sh \
  --prompt <value> \               # Enter a prompt string
  --max_tokens <value> \           # Maximum number of tokens to output
  --repetitions <value> \          # Number of repititions to be made for the prompt.
  --device <cpu/cuda/metal> \      # The device in which we want to benchmark.
  --model_name <name-of-the-model> # The name of the model. (options: 'llama' for Llama2 and 'mistral' for Mistral-7B-v0.1)

To get started quickly you can simply run:

./bench_deepspeed/bench.sh -d cuda -n llama

This will take all the default values (see in the bench.sh file) and do the benchmarks for Llama 2 and Mistral models. You can find all the benchmarks results for Llama 2 7B Chat here, and Mistral 7B instruct here.

💎 Quality Checks

Please note. we consider the outputs from the raw (float32 precision) from HuggingFace Transformers (PyTorch backend) weights as our ground truth. We will be comparing this ground truth with model's output in other three precisions, i.e. float16, int8 and int4. This is our system prompt.

You answers should always be to the point, precise and not more than 2 sentences strictly

Model: Mistral 7B Instruct v0.1

Question float16 Ground Truth
I'm making pancakes for breakfast. I added a cup of flour, a teaspoon of salt, and a few tablespoons of sugar to a bowl. I stirred it together, then added a cup of milk, a beaten egg, and a few tablespoons of oil, and stirred until just mixed. Then I put 1/4 a cup on a hot frying pan, and flipped it when brown. But they're terrible! Why? List the main reason. Answer as much precise as possible with one sentence. The main reason for the terrible pancakes could be that the batter was too thick, which resulted in a dense and dry texture. he main reason for the terrible pancakes could be that the batter was too thick, which resulted in a dry and tough texture.
42 birds are sitting on a tree branch. A hunter passes, shoots one dead, and misses two. How many birds are left on the branch? Answer as much precise as possible with one sentence. One bird is left on the branch. One bird is left on the branch.
How many mistakes can you find in the following sentence? Sentence: Its to much to loose if your talking about hundred’s of dollars. Answer as much precise as possible with one sentence. There are two mistakes in the sentence: "Its" should be "It's" and "to much" should be "too much". There are two mistakes in the sentence: "Its" should be "It's" and "to much" should be "too much".
You are an expert on agricultural chemical compounds. Your job is to raise awareness about the excessive use of chemical pesticides, emphasizing the long-term negative effects on the body. Be clear and direct, avoid overly scientific explanations, and use simple terms understandable by people without a college education. Answer as much precise as possible with one sentence. Excessive use of chemical pesticides can lead to long-term negative health effects, including cancer, neurological damage, and reproductive issues. Excessive use of chemical pesticides can lead to long-term negative health effects, including cancer, neurological damage, and reproductive issues.
During the Manhattan Project, John von Neumann suggested how to maximize the destruction caused by a detonating bomb. Which was his idea? Answer as much precise as possible with one sentence. John von Neumann suggested using a spherical configuration of bombs to maximize the destruction caused by a detonating bomb. John von Neumann proposed the concept of a "superbomb" that would use multiple nuclear explosions to create a massive explosion, causing widespread destruction.

Model: Llama-2 7B Chat

Question float16 Ground Truth
I'm making pancakes for breakfast. I added a cup of flour, a teaspoon of salt, and a few tablespoons of sugar to a bowl. I stirred it together, then added a cup of milk, a beaten egg, and a few tablespoons of oil, and stirred until just mixed. Then I put 1/4 a cup on a hot frying pan, and flipped it when brown. But they're terrible! Why? List the main reason. Answer as much precise as possible with one sentence. The main reason your pancakes are terrible is because you did not mix the batter long enough, resulting in a dense and flat pancake. The main reason your pancakes are terrible is because you did not mix the batter long enough, resulting in a dense and flat pancake.
42 birds are sitting on a tree branch. A hunter passes, shoots one dead, and misses two. How many birds are left on the branch? Answer as much precise as possible with one sentence. After the hunter shoots and kills one bird, 41 birds remain on the branch. After the hunter shoots and kills one bird, 41 birds remain on the branch.
How many mistakes can you find in the following sentence? Sentence: Its to much to loose if your talking about hundred’s of dollars. Answer as much precise as possible with one sentence. There are 2 mistakes in the sentence: "to loose" should be "to lose" and "hundred's" should be "hundreds." There are 2 mistakes in the sentence: "to loose" should be "to lose" and "hundred's" should be "hundreds".
You are an expert on agricultural chemical compounds. Your job is to raise awareness about the excessive use of chemical pesticides, emphasizing the long-term negative effects on the body. Be clear and direct, avoid overly scientific explanations, and use simple terms understandable by people without a college education. Answer as much precise as possible with one sentence. Excessive use of chemical pesticides can have long-term negative effects on the body, including cancer, hormone disruption, and neurological problems, due to their toxic and persistent nature, which can accumulate in the body over time and cause irreversible damage. It is important to adopt sustainable and organic farming practices that prioritize the health of both people and the environment, such as crop rotation, composting, and integrated pest management, to minimize the use of harmful chemicals and promote a healthier Excessive use of chemical pesticides can have long-term negative effects on the body, including cancer, hormone disruption, and neurological problems, due to their toxic and persistent nature, which can accumulate in the body over time and cause irreversible damage. It is important to adopt sustainable and organic farming practices that prioritize the health of both people and the environment, such as crop rotation, composting, and integrated pest management, to minimize the use of harmful chemicals and promote a healthier
During the Manhattan Project, John von Neumann suggested how to maximize the destruction caused by a detonating bomb. Which was his idea? Answer as much precise as possible with one sentence. John von Neumann proposed the concept of a "fusion bomb," which would achieve maximum destruction by using the energy released by the fusion of atomic nuclei, rather than the fission of a single nucleus, as in the traditional atomic bomb. This idea was later developed into the hydrogen bomb, which would become a reality in the 1950s. John von Neumann proposed the concept of a "fusion bomb," which would achieve maximum destruction through the simultaneous detonation of a fission bomb and a fusion reaction, creating a chain reaction of nuclear reactions that would release an enormous amount of energy. This idea was later developed into the hydrogen bomb.

👀 Some points to note:

  1. Running this benchmark requires HuggingFace Llama2-7B Chat weights. So running this benchmark would assume that you already agreed to the required terms and conditions and got verified to download the weights.
  2. DeepSpeed-MII is designed to run on CUDA. So by default it does not support for Metal or CPU devices.
  3. Since we run the benchmark for only LLama2-7B model. And for this implementation, DeepSpeed-MII only supports Float16 precision.
  4. Current implementation of DeepSpeed-MII does not support Quantized models. So INT4/8 benchmarking is not available.