issues
search
aws-samples
/
foundation-model-benchmarking-tool
Foundation model benchmarking tool. Run any model on any AWS platform and benchmark for performance across instance type and serving stack options.
https://aws-samples.github.io/foundation-model-benchmarking-tool/
MIT No Attribution
197
stars
31
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
hf_tokenizer change, copy s3 content update, config file updates with claude 3.5 sonnet v2
#243
madhurprash
closed
2 days ago
0
Add `hf_model_id` config param
#242
dheerajoruganty
closed
2 days ago
0
Create config-llama-3-2-1b-3b-no-evals.yml
#241
madhurprash
closed
4 days ago
0
Update and rename config-llama3.1-8b-g5.xl-g5.2xl-sm.yml to config-ll…
#240
madhurprash
closed
5 days ago
0
FMBench orchestrator bedrock + sagemaker files for llama3.1 8b
#239
madhurprash
closed
5 days ago
0
hf: replacement with globals value
#238
madhurprash
closed
6 days ago
0
New config files for llama3-8b/llama3.2-1b
#237
madhurprash
closed
1 week ago
0
updat workshop
#236
madhurprash
closed
1 week ago
0
PR for config files that will be used in the FMBench orchestrator workshop
#235
madhurprash
closed
1 week ago
0
Nous Hermes configs
#234
jimburtoft
closed
1 week ago
0
Update Sagemaker Predictor to delete EP
#233
dheerajoruganty
closed
2 weeks ago
0
Allow backup/ failover regions to be specified
#232
jimburtoft
opened
2 weeks ago
0
fix for triton ep names
#231
madhurprash
closed
2 weeks ago
0
Update config-ec2-llama3-1-70b-inf2-48xl-deploy-ec2-djl.yml
#230
aarora79
closed
2 weeks ago
0
Update config-ec2-llama3-1-70b-inf2-48xl-deploy-ec2-djl.yml
#229
aarora79
closed
2 weeks ago
0
Multimodal integration into FMBench
#228
madhurprash
closed
6 days ago
0
Add Initial support for `bge-base-en-v1-5` embedding model and Llama 3.2 11b-Vision-Instruct on FMBench
#227
dheerajoruganty
closed
2 weeks ago
3
Update pyproject.toml
#226
antara678
closed
3 weeks ago
0
Change Llama 3 8b and 70b Model IDs
#225
dheerajoruganty
closed
3 weeks ago
0
Add support for Bedrock Custom Import Models
#224
dickren123
opened
4 weeks ago
1
Add BYO Ollama Support
#223
dheerajoruganty
closed
4 weeks ago
0
Config files for all llama3.2 models - tested
#222
madhurprash
closed
1 month ago
0
make config file naming convention consistent for llama3.1 8b/70b on g6e
#221
madhurprash
closed
1 month ago
0
All config files for llama3.1 8b on g6e instances using DJL
#220
madhurprash
closed
1 month ago
0
Config files for llama3.1 8b instruct on g6e instances
#219
madhurprash
closed
1 month ago
0
changing file name for llama3 summarization prompt
#218
madhurprash
closed
1 month ago
0
adding support for llama3 summarization prompt
#217
madhurprash
closed
1 month ago
1
Configuration files for llama3.1 70b on large prompt payloads + longbench dataset
#216
madhurprash
closed
1 month ago
0
pricing update + retry logic added to bedrock predictor
#215
madhurprash
closed
1 month ago
0
add mixtral config file for AWQ version - g6e.48xl
#214
madhurprash
closed
1 month ago
0
miss warm up phase
#213
lxning
opened
1 month ago
0
Rename config-llama3-8b-g6e.4xl-tp-2-mc-max-djl-ec2.yml to config-lla…
#212
aarora79
closed
1 month ago
0
Add in g6e 2xl and 4xl files
#211
dheerajoruganty
closed
1 month ago
0
Update pricing.yml
#210
aarora79
closed
1 month ago
0
Add concurrency=3 for g6e instance configs
#209
dheerajoruganty
closed
1 month ago
0
Add config files for g6e instances
#208
dheerajoruganty
closed
1 month ago
0
Add support and pricing for g6e instances
#207
dheerajoruganty
closed
1 month ago
0
Add support for non aws models - openAI + gemini
#206
madhurprash
opened
1 month ago
0
Config file for llama3 8b on inf2 using triton with DJL
#205
madhurprash
closed
1 month ago
0
Integration triton inference server with djl
#204
madhurprash
closed
1 month ago
0
Add support for non AWS models to be benchmarked
#203
madhurprash
opened
1 month ago
0
FMBench integration: Triton Inference Server with DJL Python Backend with Transformers Neuronx
#202
madhurprash
closed
1 month ago
0
Contains a configuration file trn and doc fix for triton on AWS chips
#201
madhurprash
closed
1 month ago
0
bug fix + updated triton vllm config file
#200
madhurprash
closed
1 month ago
0
Update config-ec2-llama3-8b.yml
#199
antara678
closed
2 months ago
0
update llama2 7b quick file
#198
madhurprash
closed
2 months ago
0
Update llama2-7b quick file
#197
madhurprash
closed
2 months ago
0
Bug fix for evals
#196
madhurprash
closed
2 months ago
0
write multiple to s3 bug fix in evals
#195
madhurprash
closed
2 months ago
0
Triton integration
#194
madhurprash
closed
2 months ago
0
Next