Skip to content
CI

examples: change GPT-2 KV cache to fp16 to take advantage of tensor cores #1943

Sign in to view logs

examples: change GPT-2 KV cache to fp16 to take advantage of tensor cores

examples: change GPT-2 KV cache to fp16 to take advantage of tensor cores #1943

Triggered via pull request March 12, 2025 15:14
@bssrdfbssrdf
opened #1142
bssrdf:make-gpt-2-peform-like-llama-cpp
Status Success
Total duration 6m 45s
Artifacts –

ci.yml

on: pull_request
test-macos
2m 52s
test-macos
Matrix: build
Fit to window
Zoom out
Zoom in