Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

New Records for LLM metrics #839

Merged
merged 2 commits into from
Mar 19, 2024
Merged

Conversation

nv-braf
Copy link
Contributor

@nv-braf nv-braf commented Mar 18, 2024

I've added Records to MA for the new LLM metrics:

  • Inter Token Latency: min, max, avg, p75, p90, p99
  • Time to First Token Latency: min, max, avg, p75, p90, p99
  • Output Token Throughput

@nv-braf nv-braf requested a review from tgerdesnv March 18, 2024 17:11
@nv-braf nv-braf requested a review from tgerdesnv March 19, 2024 15:14
@nv-braf nv-braf merged commit 2156c34 into use-llm-metrics-in-ma Mar 19, 2024
3 checks passed
nv-braf added a commit that referenced this pull request Apr 8, 2024
* Adding new LLM metrics

* Adding base class for perf, inter_token, and time_to_first latency records
nv-braf added a commit that referenced this pull request Apr 8, 2024
* New Records for LLM metrics (#839)

* Adding new LLM metrics

* Adding base class for perf, inter_token, and time_to_first latency records

* Add --llm-mode option (#842)

* Adding CLI hook for LLM

* Changing to use --model-type

* Capture LLM metrics from genai-perf in MA (#844)

* Successfully reading from LLM CSV

* General cleanup

* All unit tests passing

* Fixing metric table typos

* Fixing typos

* Update constraints for LLMs (#845)

* Adding LLM values to list of possible constraints

* Fixing typo

* Adding new output fields for LLM (#846)

* Profiling model using genai-perf (#849)

* Initial changes to run genai-perf in MA

* Gating call to get LLM records

* Fixing captilization issue

* Removing debug

* Adding TODO

---------

Co-authored-by: root <[email protected]>

* Add genai_perf CLI options to MA (#854)

* Added support for genai_perf CLI

* Remove dead code

* Removing genai_perf collateral

* Fixing codeQL issue

* Adding streaming to genai_perf_config

---------

Co-authored-by: root <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

Successfully merging this pull request may close these issues.

2 participants