Skip to content

Actions: cebtenzzre/llama.cpp

Actions

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
5 workflow runs
5 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

cuda : speed-up by using CUBLAS_COMPUTE_32F instead of CUBLAS_COMPUTE… Publish Docker image #6: Commit 7c8a37b pushed by cebtenzzre
November 27, 2023 18:41 3m 50s master
master
November 27, 2023 18:41 3m 50s
Merge branch 'master' of https://github.com/ggerganov/llama.cpp Publish Docker image #5: Commit 18fe116 pushed by cebtenzzre
November 27, 2023 01:16 3m 6s master
master
November 27, 2023 01:16 3m 6s
fix loading rope.scaling.original_context_length from GGUF Publish Docker image #4: Pull request #3 synchronize by cebtenzzre
October 30, 2023 15:04 32m 24s jquesnelle:fix-orig-ctx-gguf-loading
jquesnelle:fix-orig-ctx-gguf-loading
October 30, 2023 15:04 32m 24s
fix loading rope.scaling.original_context_length from GGUF Publish Docker image #3: Pull request #3 opened by jquesnelle
October 20, 2023 16:25 20m 44s jquesnelle:fix-orig-ctx-gguf-loading
jquesnelle:fix-orig-ctx-gguf-loading
October 20, 2023 16:25 20m 44s
Fix YaRN ramp calculation and add --yarn-orig-ctx Publish Docker image #2: Pull request #2 opened by jquesnelle
October 20, 2023 04:42 23m 0s jquesnelle:ntkv2
jquesnelle:ntkv2
October 20, 2023 04:42 23m 0s