Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
54,360 workflow run results
54,360 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Document the new max GPU layers default in help EditorConfig Checker #30342: Pull request #15771 synchronize by ericcurtin
10m 32s document-new-ngl-default
document-new-ngl-default
10m 32s
Document the new max GPU layers default in help Build on RISCV Linux Machine by Cloud-V #610: Pull request #15771 synchronize by ericcurtin
18m 5s document-new-ngl-default
document-new-ngl-default
18m 5s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Server #18405: Pull request #15715 synchronize by ORippler
43m 48s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
43m 48s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Build on RISCV Linux Machine by Cloud-V #609: Pull request #15715 synchronize by ORippler
14m 18s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
14m 18s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26988: Pull request #15715 synchronize by ORippler
2h 6m 45s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
2h 6m 45s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E EditorConfig Checker #30341: Pull request #15715 synchronize by ORippler
38m 5s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
38m 5s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Pull Request Labeler #15682: Pull request #15715 synchronize by ORippler
1h 1m 6s
1h 1m 6s
Document the new max GPU layers default in help EditorConfig Checker #30340: Pull request #15771 synchronize by ericcurtin
15m 51s document-new-ngl-default
document-new-ngl-default
15m 51s
Document the new max GPU layers default in help Server #18404: Pull request #15771 synchronize by ericcurtin
16m 0s document-new-ngl-default
document-new-ngl-default
16m 0s
Document the new max GPU layers default in help CI #26987: Pull request #15771 synchronize by ericcurtin
16m 12s document-new-ngl-default
document-new-ngl-default
16m 12s
Document the new max GPU layers default in help Build on RISCV Linux Machine by Cloud-V #608: Pull request #15771 synchronize by ericcurtin
11m 28s document-new-ngl-default
document-new-ngl-default
11m 28s
Document the new max GPU layers default in help Pull Request Labeler #15681: Pull request #15771 synchronize by ericcurtin
1h 10m 36s
1h 10m 36s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26986: Pull request #15715 synchronize by ORippler
13m 18s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
13m 18s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Server #18403: Pull request #15715 synchronize by ORippler
13m 30s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
13m 30s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Build on RISCV Linux Machine by Cloud-V #607: Pull request #15715 synchronize by ORippler
22m 35s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
22m 35s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E EditorConfig Checker #30339: Pull request #15715 synchronize by ORippler
10m 12s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
10m 12s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Pull Request Labeler #15680: Pull request #15715 synchronize by ORippler
1h 10m 57s
1h 10m 57s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26985: Pull request #15715 synchronize by ORippler
17m 1s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
17m 1s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Server #18402: Pull request #15715 synchronize by ORippler
16m 58s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
16m 58s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E EditorConfig Checker #30338: Pull request #15715 synchronize by ORippler
16m 59s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
16m 59s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Build on RISCV Linux Machine by Cloud-V #606: Pull request #15715 synchronize by ORippler
34m 38s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
34m 38s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E Pull Request Labeler #15679: Pull request #15715 synchronize by ORippler
1h 26m 58s
1h 26m 58s
sampling : optimize dist sampler (#15704) CI #26984: Commit cdedb70 pushed by ggerganov
2h 11m 19s master
master
2h 11m 19s
sampling : optimize dist sampler (#15704) Server #18401: Commit cdedb70 pushed by ggerganov
1h 24m 39s master
master
1h 24m 39s
sampling : optimize dist sampler (#15704) Release #828: Commit cdedb70 pushed by ggerganov
1h 8m 52s master
master
1h 8m 52s
ProTip! You can narrow down the results and go further in time using created:<2025-09-03 or the other filters available.