bump up release number

README.md

@@ -81,6 +81,11 @@ Llama3 is now available on SageMaker (read [blog post](https://aws.amazon.com/bl
 
 ## New in this release
 
+## 2.0.9
+
+1. Triton-djl support for AWS Chips.
+1. Tokenizer files are now downloaded directly from Hugging Face (unless provided manually as before) 
+
 ## 2.0.8
 
 1. Support Triton-TensorRT for GPU instances and Triton-vllm for AWS Chips.
@@ -92,11 +97,6 @@ Llama3 is now available on SageMaker (read [blog post](https://aws.amazon.com/bl
 1. Config files for `Llama3.1-8b` on `g5`, `p4de` and `p5` Amazon EC2 instance types.
 1. Better analytics for creating internal leaderboards.
 
-## 2.0.5
-
-1. Support for Intel CPU based instances such as `c5.18xlarge` and `m5.16xlarge`.
-
-
 
 [Release history](./release_history.md)
 

docs/manifest.md

@@ -55,8 +55,7 @@ Here is a listing of the various configuration files available out-of-the-box wi
 [├── llama3/8b/config-ec2-llama3-8b-m7a-16xlarge.yml](configs/llama3/8b/config-ec2-llama3-8b-m7a-16xlarge.yml)  
 [├── llama3/8b/config-ec2-llama3-8b-m7a-24xlarge.yml](configs/llama3/8b/config-ec2-llama3-8b-m7a-24xlarge.yml)  
 [├── llama3/8b/config-ec2-llama3-8b-m7i-12xlarge.yml](configs/llama3/8b/config-ec2-llama3-8b-m7i-12xlarge.yml)  
-[├── llama3/8b/config-ec2-llama3-8b-neuron-trn1-32xl-tp16-sm.yml](configs/llama3/8b/config-ec2-llama3-8b-neuron-trn1-32xl-tp16-sm.yml)
-[├── config-llama3-8b-trn1-32xl-tp16-bs-4-ec2.yml](config-llama3-8b-trn1-32xl-tp16-bs-4-ec2.yml)
+[├── llama3/8b/config-ec2-llama3-8b-neuron-trn1-32xl-tp16-sm.yml](configs/llama3/8b/config-ec2-llama3-8b-neuron-trn1-32xl-tp16-sm.yml)  
 [├── llama3/8b/config-ec2-llama3-8b.yml](configs/llama3/8b/config-ec2-llama3-8b.yml)  
 [├── llama3/8b/config-ec2-neuron-llama3-8b-inf2-24xl-deploy-sm.yml](configs/llama3/8b/config-ec2-neuron-llama3-8b-inf2-24xl-deploy-sm.yml)  
 [├── llama3/8b/config-ec2-neuron-llama3-8b-inf2-48xl-deploy-sm.yml](configs/llama3/8b/config-ec2-neuron-llama3-8b-inf2-48xl-deploy-sm.yml)  
@@ -85,6 +84,8 @@ Here is a listing of the various configuration files available out-of-the-box wi
 [├── llama3/8b/config-llama3-8b-instruct-p5-djl-lmi-dist.yml](configs/llama3/8b/config-llama3-8b-instruct-p5-djl-lmi-dist.yml)  
 [├── llama3/8b/config-llama3-8b-trn1-32xl-tp-16-bs-4-byoe.yml](configs/llama3/8b/config-llama3-8b-trn1-32xl-tp-16-bs-4-byoe.yml)  
 [├── llama3/8b/config-llama3-8b-trn1-32xl-tp-8-bs-4-byoe.yml](configs/llama3/8b/config-llama3-8b-trn1-32xl-tp-8-bs-4-byoe.yml)  
+[├── llama3/8b/config-llama3-8b-trn1-32xl-tp16-bs-4-ec2.yml](configs/llama3/8b/config-llama3-8b-trn1-32xl-tp16-bs-4-ec2.yml)  
+[├── llama3/8b/config-llama3-8b-trn1-32xlarge-triton-djl.yml](configs/llama3/8b/config-llama3-8b-trn1-32xlarge-triton-djl.yml)  
 [├── llama3/8b/config-llama3-8b-trn1-32xlarge-triton-vllm.yml](configs/llama3/8b/config-llama3-8b-trn1-32xlarge-triton-vllm.yml)  
 [├── llama3/8b/config-llama3-8b-trn1.yml](configs/llama3/8b/config-llama3-8b-trn1.yml)  
 [├── llama3/8b/llama3-8b-inf2-24xl-byoe-g5-12xl.yml](configs/llama3/8b/llama3-8b-inf2-24xl-byoe-g5-12xl.yml)  
@@ -141,4 +142,4 @@ Here is a listing of the various configuration files available out-of-the-box wi
 [model_eval_all_info.yml](configs/model_eval_all_info.yml)  
 **phi**  
 [└── phi/config-phi-3-g5.yml]( configs/phi/config-phi-3-g5.yml)  
-[pricing.yml](configs/pricing.yml)  
+[pricing.yml](configs/pricing.yml)  

docs/releases.md

@@ -1,5 +1,10 @@
 # Releases
 
+## 2.0.9
+
+1. Triton-djl support for AWS Chips.
+1. Tokenizer files are now downloaded directly from Hugging Face (unless provided manually as before) 
+
 ## 2.0.7
 
 1. Support Triton-TensorRT for GPU instances and Triton-vllm for AWS Chips.

manifest.txt

@@ -63,7 +63,6 @@ configs/llama3/70b/config-llama3-70b-instruct-g5-48xl.yml
 configs/llama3/70b/config-llama3-70b-instruct-g5-p4d.yml
 configs/llama3/70b/config-llama3-70b-instruct-p4d.yml
 configs/llama3/8b/config-bedrock.yml
-configs/llama3/8b/config-llama3-8b-trn1-32xl-tp16-bs-4-ec2.yml
 configs/llama3/8b/config-ec2-llama3-8b-c5-18xlarge.yml
 configs/llama3/8b/config-ec2-llama3-8b-inf2-48xl.yml
 configs/llama3/8b/config-ec2-llama3-8b-m5-16xlarge.yml
@@ -99,6 +98,8 @@ configs/llama3/8b/config-llama3-8b-instruct-p4d-djl-vllm.yml
 configs/llama3/8b/config-llama3-8b-instruct-p5-djl-lmi-dist.yml
 configs/llama3/8b/config-llama3-8b-trn1-32xl-tp-16-bs-4-byoe.yml
 configs/llama3/8b/config-llama3-8b-trn1-32xl-tp-8-bs-4-byoe.yml
+configs/llama3/8b/config-llama3-8b-trn1-32xl-tp16-bs-4-ec2.yml
+configs/llama3/8b/config-llama3-8b-trn1-32xlarge-triton-djl.yml
 configs/llama3/8b/config-llama3-8b-trn1-32xlarge-triton-vllm.yml
 configs/llama3/8b/config-llama3-8b-trn1.yml
 configs/llama3/8b/llama3-8b-inf2-24xl-byoe-g5-12xl.yml
@@ -135,4 +136,4 @@ source_data/hotpotqa_e.jsonl
 source_data/narrativeqa.jsonl
 source_data/triviaqa.jsonl
 source_data/triviaqa_e.jsonl
-tokenizer/.keep
+tokenizer/.keep

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "fmbench"
-version = "2.0.8"
+version = "2.0.9"
 description ="Benchmark performance of **any Foundation Model (FM)** deployed on **any AWS Generative AI service**, be it **Amazon SageMaker**, **Amazon Bedrock**, **Amazon EKS**, or **Amazon EC2**. The FMs could be deployed on these platforms either directly through `FMbench`, or, if they are already deployed then also they could be benchmarked through the **Bring your own endpoint** mode supported by `FMBench`."
 authors = ["Amit Arora <[email protected]>", "Madhur Prashant <[email protected]>"]
 readme = "README.md"

release_history.md

@@ -1,3 +1,7 @@
+## 2.0.5
+
+1. Support for Intel CPU based instances such as `c5.18xlarge` and `m5.16xlarge`.
+
 ## 2.0.4
 
 1. Support for AMD CPU based instances such as `m7a`.