Skip to content
Back to pull request #4213

Allow reusing results from llama_token_to_piece when sampling grammars #6556

Sign in to view logs

Allow reusing results from llama_token_to_piece when sampling grammars

Allow reusing results from llama_token_to_piece when sampling grammars #6556

Triggered via pull request November 25, 2023 04:59
@MarcusDunnMarcusDunn
opened #4213
grammar_cache_tokens
Status Success
Total duration 19m 1s
Artifacts –

build.yml

on: pull_request
Matrix: windows-latest-cmake-cublas
Matrix: windows-latest-cmake
ubuntu-focal-make
1m 23s
ubuntu-focal-make
ubuntu-latest-cmake
1m 21s
ubuntu-latest-cmake
macOS-latest-make
1m 36s
macOS-latest-make
macOS-latest-cmake
4m 33s
macOS-latest-cmake
macOS-latest-cmake-ios
1m 25s
macOS-latest-cmake-ios
macOS-latest-cmake-tvos
1m 45s
macOS-latest-cmake-tvos
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-mpi
Matrix: ubuntu-latest-cmake-sanitizer
release
0s
release
Fit to window
Zoom out
Zoom in

Annotations

1 error
windows-latest-cmake (avx512, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUIL...
Process completed with exit code 1.