LP: vllm benchmarking with quantised models#3207

Merged

pareenaverma merged 8 commits into

ArmDeveloperEcosystem:mainfrom

almayne:vllm_bench_quantised

May 15, 2026

Commits on Apr 24, 2026

LP: vllm benchmarking with quantised models
almayne
committed

Commits on Apr 27, 2026

Commits on May 1, 2026

Reordered pages and switched quant recipe to w8a8. Updated inference page to use custom scripts and added whisper inference back in. Accuracy results in benchmarking page are now full runs.
almayne
committed

Commits on May 14, 2026

Commits on May 15, 2026

Update _index.md
pareenaverma
authored