Benchmarks v2 Merging dev to main #184
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ks (#163) * Added info about mistral support * AutoGPTQ now uses base class, with mistral support and memory profiling * minor changes on change of cli args in bench.sh * changed requirements with latest update of autogptq * support for mistral instruct and llama2 chat and latest autogptq installation from source * Added another common utility to build chat templates for model * fix bugs for multiple duplicated logging * PyTorchBenchmark supports mistral, memory profile and uses Base class * changes in instruction and using latest model for benchmarking, removed Logs * fixing dependencies with proper versions * Addition of mistral and llama and also table for precision wise quality comparision * Added new docs and template for mistral and starting out new benchmark performance logs in templates * improvements on better logging strategies to log the quality checks output in a readme * integrated the utility for logging improvements * using better logging stratgies in bench pytorch * questions.json has the ground truth answer set from fp32 response * AutoGPTQ readme improvements and added quality checks examples for llama and mistral * Using latest logging utilities * removed creation of Logs folder and unnencessary arguments * Added fsspec * Added llama2 and mistral performance logs * pinned version of huggingface_hub * Latest info under 'some points to note' section * Update bench_autogptq/bench.sh Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it> --------- Co-authored-by: Anindyadeep Sannigrahi <anindyadeepsannigrahi@Anindyadeeps-MacBook-Pro.local> Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it>
…cks (#168) * Added another common utility to build chat templates for model * fix bugs for multiple duplicated logging * PyTorchBenchmark supports mistral, memory profile and uses Base class * changes in instruction and using latest model for benchmarking, removed Logs * fixing dependencies with proper versions * Addition of mistral and llama and also table for precision wise quality comparision * Added new docs and template for mistral and starting out new benchmark performance logs in templates * improvements on better logging strategies to log the quality checks output in a readme * integrated the utility for logging improvements * using better logging stratgies in bench pytorch * questions.json has the ground truth answer set from fp32 response * DeepSpeed now using base class, mistral support and memory profiling * removed unused imports * removed Logs and latest improvements w.r.t base class * README now has quality comparision for deepspeed * using latest version of deepspeed * added latest performance logs for llama2 and mistral * added docs for llama and mistral with latest scores * updated readme with correct model info --------- Co-authored-by: Anindyadeep Sannigrahi <anindyadeepsannigrahi@Anindyadeeps-MacBook-Pro.local>
* Ctransformers support mistral and uses Base class along with memory profiling * uses latest bench.py arguments, remove making log folders and improvements * supporting mistral and llama chat models and installation improvements * added additional requirements which is not support by ctransformers by default * Added another common utility to build chat templates for model * fix bugs for multiple duplicated logging * PyTorchBenchmark supports mistral, memory profile and uses Base class * changes in instruction and using latest model for benchmarking, removed Logs * fixing dependencies with proper versions * Addition of mistral and llama and also table for precision wise quality comparision * Added new docs and template for mistral and starting out new benchmark performance logs in templates * improvements on better logging strategies to log the quality checks output in a readme * integrated the utility for logging improvements * using better logging stratgies in bench pytorch * questions.json has the ground truth answer set from fp32 response * CTransformers using latest logging utilities * removed unnecessary arguments and creation of Logs folder * Add precision wise quality comparision on AutoGPTQ readme * Added performance scores for llama2 and mistral * Latest info under 'some points to note' section * added ctransformers performance logs for mistral and llama * Update bench_ctransformers/bench.sh Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it> --------- Co-authored-by: Anindyadeep Sannigrahi <anindyadeepsannigrahi@Anindyadeeps-MacBook-Pro.local> Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it>
* Added support for BaseClass and mistral with memory profiling * removed docker support with latest ctranslate release * Added latest ctranslate2 version * Removed runs with docker and added mistral model support * removed docker support and added mistral support * Added performance logs for mistral and llama * engine specific readme with qualitative comparision
* fix bug: handle temperature when None * Added llamacpp engine readme with quality comparision * Using Base class with mistral support and memory profiling * shell script cli improvements * Added newer requirements with version pineed * small improvements * removed MODEL_NAME while running setup * Added performance logs for llama and mistral
Fix Transformers benchmark numbers
…ements (#175) * Added performance logs for mistral and llama for exllamav2 along with qualitative comparisions * ExLlamaV2 using base class along with support for mistral and memory profiling * removed old cli args and small improvements * deleted convert.py script * pinned latest version and added transformers * addition of mistral model along with usage of latest exllamav2 repo * Update bench_exllamav2/bench.sh Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it> --------- Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it>
#172) * Adding base class with mistral support and memory profling * small improvements on removing unnecessary cli args * download support for mistral * adding on_exit function on get_answers * Added precision wise qualitative checks for vLLM README * Added performance logs on docs for mistral and llama * Update bench_vllm/bench.sh Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it> --------- Co-authored-by: Nicola Sosio <sosio.nicola94@tiscali.it>
… and improvements (#178) * Added readme with mistral support and qualitative comparision * TRT LLM using base class with mistral and memory profiling support * removed old cli args, and some improvements * Added support for mistral with latest trt llm * Added support for root dir for handling runs inside and outside docker * Added performance logs for both mistral and llama * Added float32 on docs and performance logs * Added support for float32 precision * Added support for float32 * revised to int4 for mistral
…mprovements (#177) * Added performance logs for mistral and llama for exllamav2 along with qualitative comparisions * ExLlamaV2 using base class along with support for mistral and memory profiling * removed old cli args and small improvements * deleted convert.py script * pinned latest version and added transformers * addition of mistral model along with usage of latest exllamav2 repo * Using base benchmark class with memory profiling support and mistral model support * Addition of new contructor argument root_dir to handle paths inside or outside docker * created a converter script to convert to tensorrt engine file * Addition of latest update usage of optimum nvidia and also added qualitative comparision * cli improvements and remove older cli args * added latest conversion script logic to conver hf weights to engine and mistral support * Added latest performance logs for both mistral and llama * removed the conflict with exllamav2 * removed changes from exllamav2
* Added comparative quality analysis for mistral and llama and also added nuances related to onnx * Using base class with memory profiling and mistral support * removed old cli arguments and some improvements * removed requirements, since onnx runs using custom docker container * Added new setup sh file with mistral and llama onnx conversion through docker * Added performance logs of onnx for llama and mistral
* Added qualitative comparision of quantity for litgpt * Using base class with mistral support and memory support * small cli improvements, removed old arguments * removed convert logic with latest litgpt * Added latest inference logic code * pinned version for dependencies * Added latest method of installation and model conversions with litgpt * added performance benchmarks info in litgpt * updated the memory usage and token per seconds * chore: minor improvements and added latest info about int4
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.