Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
70,632 workflow run results
70,632 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

cpu: introduce chunking for flash attention
Pull Request Labeler #18372: Pull request #16829 opened by max-krasnyansky
1h 10m 5s
llama: store mrope data in KV cell
Build on RISCV Linux Machine by Cloud-V #2987: Pull request #16825 synchronize by ngxson
llama: store mrope data in KV cell
Pull Request Labeler #18371: Pull request #16825 synchronize by ngxson
1h 17m 19s
CUDA: Conv2d tensor core
Pull Request Labeler #18370: Pull request #16828 opened by mnehete32
57m 40s
Build Actions Cache
Build Actions Cache #534: Scheduled
1h 7m 11s master
Massively Improved ROCm/HIP rocWMMA Performance (pp and tg)
Pull Request Labeler #18369: Pull request #16827 opened by lhl
1h 36m 9s
vulkan: remove the need for the dryrun
Build on RISCV Linux Machine by Cloud-V #2984: Pull request #16826 opened by jeffbolznv
vulkan: remove the need for the dryrun
Pull Request Labeler #18368: Pull request #16826 opened by jeffbolznv
1h 28m 31s
cuda: add SET operation support (#16804)
EditorConfig Checker #33158: Commit 851553e pushed by JohannesGaessler
1h 32m 53s master
Build Actions Cache
Build Actions Cache #533: Scheduled
1h 31m 0s master
server : remove n_past
Build on RISCV Linux Machine by Cloud-V #2983: Pull request #16818 synchronize by ggerganov