Open
Conversation
Co-authored-by: Natalia Groza <natalia.groza@intel.com>
dkalinowski
approved these changes
Feb 27, 2026
dkalinowski
approved these changes
Feb 27, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the continuous batching accuracy demo documentation to reflect newer Llama 3.1 model IDs and to standardize the command examples for Linux shell usage.
Changes:
- Switches Meta-Llama model references from Llama 3 to Llama 3.1 in export and
lm-evalexamples. - Standardizes code fences to
bashand adds a note that steps were verified on Linux.
Comment on lines
+44
to
+46
| lm-eval --model local-chat-completions --tasks gsm8k --model_args model=meta-llama/Meta-Llama-3.1-8B-Instruct,base_url=http://localhost:8000/v3/chat/completions,num_concurrent=1,max_retries=3,tokenized_requests=False --verbosity DEBUG --log_samples --output_path test/ --seed 1 --apply_chat_template --limit 100 | ||
|
|
||
| local-chat-completions ({'model': 'meta-llama/Meta-Llama-3-8B-Instruct', 'base_url': 'http://localhost:8000/v3/chat/completions', 'num_concurrent': 10, 'max_retries': 3, 'tokenized_requests': False}), gen_kwargs: ({}), limit: 100.0, num_fewshot: None, batch_size: 1 | ||
| local-chat-completions ({'model': 'meta-llama/Meta-Llama-3.1-8B-Instruct', 'base_url': 'http://localhost:8000/v3/chat/completions', 'num_concurrent': 10, 'max_retries': 3, 'tokenized_requests': False}), gen_kwargs: ({}), limit: 100.0, num_fewshot: None, batch_size: 1 |
There was a problem hiding this comment.
The example output shows num_concurrent: 10 while the command above sets num_concurrent=1. This is confusing for readers trying to reproduce the run; please make the command and the captured output consistent (either update the command args or regenerate/update the output snippet).
| ```console | ||
| lm-eval --model local-completions --tasks gsm8k --model_args model=meta-llama/Meta-Llama-3-8B,base_url=http://localhost:8000/v3/completions,num_concurrent=1,max_retries=3,tokenized_requests=False --verbosity DEBUG --log_samples --output_path results/ --seed 1 --limit 100 | ||
| ```bash | ||
| lm-eval --model local-completions --tasks gsm8k --model_args model=meta-llama/Meta-Llama-3.1-8B,base_url=http://localhost:8000/v3/completions,num_concurrent=1,max_retries=3,tokenized_requests=False --verbosity DEBUG --log_samples --output_path results/ --seed 1 --limit 100 |
There was a problem hiding this comment.
The example output shows num_concurrent: 10 while the command above sets num_concurrent=1. Please align the command and the captured output snippet so the documentation is reproducible.
Suggested change
| lm-eval --model local-completions --tasks gsm8k --model_args model=meta-llama/Meta-Llama-3.1-8B,base_url=http://localhost:8000/v3/completions,num_concurrent=1,max_retries=3,tokenized_requests=False --verbosity DEBUG --log_samples --output_path results/ --seed 1 --limit 100 | |
| lm-eval --model local-completions --tasks gsm8k --model_args model=meta-llama/Meta-Llama-3.1-8B,base_url=http://localhost:8000/v3/completions,num_concurrent=10,max_retries=3,tokenized_requests=False --verbosity DEBUG --log_samples --output_path results/ --seed 1 --limit 100 |
| The [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) framework provides a convenient method of evaluating the quality of the model exposed over OpenAI API. | ||
| It reports end to end quality of served model from the client application point of view. | ||
|
|
||
| **Note**: Below steps have been verified on Linux |
There was a problem hiding this comment.
Minor grammar/punctuation: consider adding a period and/or clarifying the scope (e.g., "verified on Linux only") so readers on other OSes know what to expect.
Suggested change
| **Note**: Below steps have been verified on Linux | |
| **Note:** The following steps have been verified on Linux only. |
ngrozae
approved these changes
Feb 27, 2026
This file contains hidden or 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
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.