Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
44,009 workflow run results
44,009 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA: add softmax broadcast
Pull Request Labeler #12999: Pull request #14475 synchronize by am17an
10s
ggml: backward pass for split swiglu
Pull Request Labeler #12998: Pull request #14483 opened by JohannesGaessler
12m 18s
llama : reuse compute graphs
Pull Request Labeler #12997: Pull request #14482 opened by ggerganov
11s
Callback before abort
Pull Request Labeler #12996: Pull request #14481 opened by ScaledLizard
1m 21s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops
Pull Request Labeler #12995: Pull request #14445 synchronize by CISC
7m 13s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops
Pull Request Labeler #12994: Pull request #14445 synchronize by CISC
20m 35s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops
Pull Request Labeler #12993: Pull request #14445 synchronize by CISC
28s
CUDA: add softmax broadcast
Pull Request Labeler #12992: Pull request #14475 synchronize by am17an
25m 46s
ProTip! You can narrow down the results and go further in time using created:<2025-07-01 or the other filters available.