Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
35,029 workflow run results
35,029 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : vision support via libmtmd Pull Request Labeler #10986: Pull request #12898 synchronize by ngxson
2h 42m 56s
2h 42m 56s
llama : try loading tensors with pre-computed hashes Server #13707: Pull request #13106 synchronize by rgerganov
3h 9m 0s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
3h 9m 0s
llama : try loading tensors with pre-computed hashes CI #22340: Pull request #13106 synchronize by rgerganov
3h 50m 10s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
3h 50m 10s
llama : try loading tensors with pre-computed hashes EditorConfig Checker #25048: Pull request #13106 synchronize by rgerganov
42m 40s rgerganov:rpc-load-tensor
rgerganov:rpc-load-tensor
42m 40s
llama : try loading tensors with pre-computed hashes Pull Request Labeler #10985: Pull request #13106 synchronize by rgerganov
2h 38m 10s
2h 38m 10s
kv-cache : add SWA support CI #22339: Pull request #13194 synchronize by ggerganov
3h 56m 2s gg/swa
gg/swa
3h 56m 2s
kv-cache : add SWA support EditorConfig Checker #25047: Pull request #13194 synchronize by ggerganov
1h 18m 59s gg/swa
gg/swa
1h 18m 59s
kv-cache : add SWA support Server #13706: Pull request #13194 synchronize by ggerganov
1h 23m 57s gg/swa
gg/swa
1h 23m 57s
kv-cache : add SWA support Pull Request Labeler #10984: Pull request #13194 synchronize by ggerganov
2h 26m 40s
2h 26m 40s
kv-cache : prepare for SWA (wip) Python Type-Check #2579: Commit 1e10743 pushed by ggerganov
44m 14s gg/swa
gg/swa
44m 14s
metal : optimize MoE for large batches (#13388) Release #16: Commit 611aa91 pushed by ggerganov
4h 24m 34s master
master
4h 24m 34s
metal : optimize MoE for large batches (#13388) CI #22338: Commit 611aa91 pushed by ggerganov
4h 54m 47s master
master
4h 54m 47s
metal : optimize MoE for large batches (#13388) EditorConfig Checker #25046: Commit 611aa91 pushed by ggerganov
52m 25s master
master
52m 25s
metal : optimize MoE for large batches (#13388) Server #13705: Commit 611aa91 pushed by ggerganov
2h 9m 9s master
master
2h 9m 9s
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs CI #22337: Pull request #12858 synchronize by Alcpz
3h 5m 28s Alcpz:Alcpz/mmvq_q4_0_reorder
Alcpz:Alcpz/mmvq_q4_0_reorder
3h 5m 28s
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs EditorConfig Checker #25045: Pull request #12858 synchronize by Alcpz
17m 18s Alcpz:Alcpz/mmvq_q4_0_reorder
Alcpz:Alcpz/mmvq_q4_0_reorder
17m 18s
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs Pull Request Labeler #10983: Pull request #12858 synchronize by Alcpz
1h 21m 32s
1h 21m 32s
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs Server #13704: Pull request #12858 synchronize by Alcpz
1h 35m 5s Alcpz:Alcpz/mmvq_q4_0_reorder
Alcpz:Alcpz/mmvq_q4_0_reorder
1h 35m 5s
CUDA: FA support for Deepseek (Ampere or newer) (#13306) Python Type-Check #2578: Commit 0cf6725 pushed by JohannesGaessler
34m 43s master
master
34m 43s
CUDA: FA support for Deepseek (Ampere or newer) (#13306) flake8 Lint #18112: Commit 0cf6725 pushed by JohannesGaessler
35m 18s master
master
35m 18s
CUDA: FA support for Deepseek (Ampere or newer) (#13306) EditorConfig Checker #25044: Commit 0cf6725 pushed by JohannesGaessler
35m 32s master
master
35m 32s
CUDA: FA support for Deepseek (Ampere or newer) (#13306) CI #22336: Commit 0cf6725 pushed by JohannesGaessler
4h 51m 16s master
master
4h 51m 16s
CUDA: FA support for Deepseek (Ampere or newer) (#13306) Server #13703: Commit 0cf6725 pushed by JohannesGaessler
58m 16s master
master
58m 16s
CUDA: FA support for Deepseek (Ampere or newer) (#13306) Release #15: Commit 0cf6725 pushed by JohannesGaessler
1h 54m 33s master
master
1h 54m 33s
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs Pull Request Labeler #10982: Pull request #12063 synchronize by chraac
44m 32s
44m 32s