Skip to content

Rename Inference Benchmarks section to Inference Metrics #5

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.

Sign up for GitHub

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

Merged
geethac2l merged 1 commit into from
Apr 9, 2026
Merged

Rename Inference Benchmarks section to Inference Metrics #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ Microservices-based AI application that converts PDF, DOC, and DOCX documents in
- [Quick Start](#quick-start)
- [Project Structure](#project-structure)
- [Usage Guide](#usage-guide)
- [Inference Benchmarks](#inference-benchmarks)
- [Inference Metrics](#inference-metrics)
- [Model Capabilities](#model-capabilities)
- [Environment Variables](#environment-variables)
- [Technology Stack](#technology-stack)
Expand Down Expand Up @@ -388,7 +388,7 @@ Audify/

---

## Inference Benchmarks
## Inference Metrics

The table below compares inference performance across different providers, deployment modes, and hardware profiles using a standardized Audify script-generation workload averaged over 3 runs.

Expand All @@ -402,7 +402,7 @@ The table below compares inference performance across different providers, deplo
>
> - Context Window for vLLM (4,096) reflects the `LLM_MAX_TOKENS` / `--max-model-len` used during benchmarking, not the model's native maximum context. vLLM shares its configured context between input and output tokens.
> - EI is configured with an 8,192-token context window for this benchmark run.
> - All benchmarks use the same Audify script-generation prompt and identical inputs across 3 runs.
> - All metrics use the same Audify script-generation prompt and identical inputs across 3 runs.
> - Token counts may vary slightly per run due to non-deterministic model output.
> - vLLM on Apple Silicon requires [vllm-metal](https://github.com/vllm-project/vllm-metal); the standard `pip install vllm` package does not provide macOS Metal support.
> - [Intel OPEA EI](https://github.com/opea-project/Enterprise-Inference) runs on Intel Xeon CPUs without GPU acceleration.
Expand Down
Loading