Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
44,691 workflow run results
44,691 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA: add dynamic shared mem to softmax, refactor general usage (#14497) Server #15809: Commit 55c2646 pushed by am17an
11m 41s master
master
11m 41s
CUDA: add dynamic shared mem to softmax, refactor general usage (#14497) Release #391: Commit 55c2646 pushed by am17an
1h 8m 52s master
master
1h 8m 52s
CUDA: add dynamic shared mem to softmax, refactor general usage (#14497) CI #24414: Commit 55c2646 pushed by am17an
59m 20s master
master
59m 20s
CUDA: add dynamic shared mem to softmax, refactor general usage (#14497) EditorConfig Checker #27395: Commit 55c2646 pushed by am17an
19s master
master
19s
vulkan: support mixed/deepseekR1 FA head sizes CI #24413: Pull request #14509 synchronize by jeffbolznv
1h 4m 39s jeffbolznv:fa_head_sizes
jeffbolznv:fa_head_sizes
1h 4m 39s
vulkan: support mixed/deepseekR1 FA head sizes Server #15808: Pull request #14509 synchronize by jeffbolznv
13m 24s jeffbolznv:fa_head_sizes
jeffbolznv:fa_head_sizes
13m 24s
vulkan: support mixed/deepseekR1 FA head sizes EditorConfig Checker #27394: Pull request #14509 synchronize by jeffbolznv
18s jeffbolznv:fa_head_sizes
jeffbolznv:fa_head_sizes
18s
vulkan: support mixed/deepseekR1 FA head sizes Pull Request Labeler #13060: Pull request #14509 synchronize by jeffbolznv
9s
9s
Granite Four Server #15807: Pull request #13550 synchronize by gabe-l-hart
19m 25s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
19m 25s
Granite Four Python Type-Check #3149: Pull request #13550 synchronize by gabe-l-hart
5m 7s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
5m 7s
Granite Four Python check requirements.txt #3459: Pull request #13550 synchronize by gabe-l-hart
8m 22s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
8m 22s
Granite Four flake8 Lint #18559: Pull request #13550 synchronize by gabe-l-hart
15s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
15s
Granite Four EditorConfig Checker #27393: Pull request #13550 synchronize by gabe-l-hart
16s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
16s
Granite Four CI #24412: Pull request #13550 synchronize by gabe-l-hart
6h 7m 36s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
6h 7m 36s
Granite Four Pull Request Labeler #13059: Pull request #13550 synchronize by gabe-l-hart
10s
10s
vulkan: support mixed/deepseekR1 FA head sizes Pull Request Labeler #13058: Pull request #14509 opened by jeffbolznv
10s
10s
tests : enhance llama-bench with separate timings (pp/gen t/s), added n_threads_batch Pull Request Labeler #13057: Pull request #14219 synchronize by thad0ctor
9s
9s
logit_bias: apply configurable escalating EOG bias at low n_remain Pull Request Labeler #13056: Pull request #14229 synchronize by graehl
4m 19s
4m 19s
gguf-py : add support for chat template jinja files (#14508) EditorConfig Checker #27391: Commit e75ba4c pushed by CISC
7m 32s master
master
7m 32s
gguf-py : add support for chat template jinja files (#14508) Python check requirements.txt #3458: Commit e75ba4c pushed by CISC
3m 38s master
master
3m 38s
gguf-py : add support for chat template jinja files (#14508) flake8 Lint #18558: Commit e75ba4c pushed by CISC
3m 59s master
master
3m 59s
gguf-py : add support for chat template jinja files (#14508) Python Type-Check #3148: Commit e75ba4c pushed by CISC
5m 20s master
master
5m 20s
llama : add high-throughput mode Server #15805: Pull request #14363 synchronize by ggerganov
45m 1s gg/llama-high-throughput
gg/llama-high-throughput
45m 1s
llama : add high-throughput mode CI #24410: Pull request #14363 synchronize by ggerganov
1h 32m 52s gg/llama-high-throughput
gg/llama-high-throughput
1h 32m 52s
llama : add high-throughput mode Pull Request Labeler #13055: Pull request #14363 synchronize by ggerganov
27m 46s
27m 46s