Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
85,088 workflow runs
85,088 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

graph: add f_attn_temp_offset (#18025) EditorConfig Checker #36570: Commit 0759b09 pushed by ngxson
Queued master
master
Queued
ggml-blas: refactor BLAS backend CI #32298: Pull request #18027 opened by taronaeo
31m 37s taronaeo:feat/blas_mmid
taronaeo:feat/blas_mmid
31m 37s
ggml-blas: refactor BLAS backend Server #23970: Pull request #18027 opened by taronaeo
Queued taronaeo:feat/blas_mmid
taronaeo:feat/blas_mmid
Queued
ggml-blas: refactor BLAS backend EditorConfig Checker #36569: Pull request #18027 opened by taronaeo
1h 49m 43s taronaeo:feat/blas_mmid
taronaeo:feat/blas_mmid
1h 49m 43s
ggml-blas: refactor BLAS backend Pull Request Labeler #21501: Pull request #18027 opened by taronaeo
1h 49m 39s
1h 49m 39s
vulkan: fix mul_mat_vec_iq1_s formatting CI #32297: Pull request #18026 opened by 0cc4m
Queued 0cc4m/vulkan-fix-iq1s-indent
0cc4m/vulkan-fix-iq1s-indent
Queued
vulkan: fix mul_mat_vec_iq1_s formatting EditorConfig Checker #36568: Pull request #18026 opened by 0cc4m
1h 25m 39s 0cc4m/vulkan-fix-iq1s-indent
0cc4m/vulkan-fix-iq1s-indent
1h 25m 39s
vulkan: fix mul_mat_vec_iq1_s formatting Pull Request Labeler #21500: Pull request #18026 opened by 0cc4m
1h 50m 37s
1h 50m 37s
graph: add f_attn_temp_offset CI #32296: Pull request #18025 opened by ngxson
Queued xsn/llama4_scaling_offset
xsn/llama4_scaling_offset
Queued
graph: add f_attn_temp_offset EditorConfig Checker #36567: Pull request #18025 opened by ngxson
1h 59m 11s xsn/llama4_scaling_offset
xsn/llama4_scaling_offset
1h 59m 11s
graph: add f_attn_temp_offset Server #23969: Pull request #18025 opened by ngxson
Queued xsn/llama4_scaling_offset
xsn/llama4_scaling_offset
Queued
graph: add f_attn_temp_offset Pull Request Labeler #21499: Pull request #18025 opened by ngxson
2h 17m 27s
2h 17m 27s
server: add /v1/metrics endpoint CI #32295: Pull request #18001 synchronize by Kritavya
Action required Kritavya:master
Kritavya:master
Action required
server: add /v1/metrics endpoint Server #23968: Pull request #18001 synchronize by Kritavya
Action required Kritavya:master
Kritavya:master
Action required
server: add /v1/metrics endpoint EditorConfig Checker #36566: Pull request #18001 synchronize by Kritavya
Action required Kritavya:master
Kritavya:master
Action required
server: add /v1/metrics endpoint Pull Request Labeler #21498: Pull request #18001 synchronize by Kritavya
2h 15m 21s
2h 15m 21s
Build Actions Cache Build Actions Cache #1653: Scheduled
2h 13m 17s master
master
2h 13m 17s
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization CI #32294: Pull request #16653 synchronize by JohannesGaessler
Queued JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
Queued
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization EditorConfig Checker #36565: Pull request #16653 synchronize by JohannesGaessler
1h 59m 28s JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
1h 59m 28s
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization Server #23967: Pull request #16653 synchronize by JohannesGaessler
Queued JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
Queued
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization Pull Request Labeler #21497: Pull request #16653 synchronize by JohannesGaessler
2h 25m 6s
2h 25m 6s
Build Actions Cache Build Actions Cache #1652: Scheduled
2h 22m 40s master
master
2h 22m 40s
implement Power Law sampling Pull Request Labeler #21496: Pull request #17927 synchronize by ddh0
3h 0m 5s
3h 0m 5s
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization CI #32293: Pull request #16653 synchronize by JohannesGaessler
1h 2m 31s JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
1h 2m 31s
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization EditorConfig Checker #36564: Pull request #16653 synchronize by JohannesGaessler
1h 2m 15s JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
1h 2m 15s