Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
8,132 workflow run results
8,132 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA: add softmax broadcast CI #24335: Pull request #14475 opened by am17an
25m 16s am17an:add_softmax_batch_and_broadcast
am17an:add_softmax_batch_and_broadcast
25m 16s
ggml : support broadcast for ggml_soft_max_ext and ggml_flash_attn_ext CI #24334: Pull request #14435 synchronize by 0cc4m
2h 13m 27s gg/ggml-batch-soft-max-ops
gg/ggml-batch-soft-max-ops
2h 13m 27s
add GELU_ERF (#14455) CI #24333: Commit eff5e45 pushed by 0cc4m
4h 15m 17s master
master
4h 15m 17s
sync : ggml CI #24332: Pull request #14473 synchronize by ggerganov
3h 23m 28s sync-ggml-25-07-01
sync-ggml-25-07-01
3h 23m 28s
ggml : remove trailing whitespace (#0) CI #24331: Commit a6a4795 pushed by ggerganov
1h 52m 57s master
master
1h 52m 57s
sync : ggml CI #24330: Pull request #14473 synchronize by ggerganov
1h 53m 39s sync-ggml-25-07-01
sync-ggml-25-07-01
1h 53m 39s
sync : ggml CI #24329: Pull request #14473 opened by ggerganov
38m 49s sync-ggml-25-07-01
sync-ggml-25-07-01
38m 49s
opencl : add GEGLU, REGLU, SWIGLU (#14456) CI #24328: Commit 79b33b2 pushed by CISC
1h 4m 15s master
master
1h 4m 15s
Q2k interleaving implementation - x86/x64 SIMD CI #24327: Pull request #14373 synchronize by Srihari-mcw
53m 52s Srihari-mcw:q2k_interleaving_implementation
Srihari-mcw:q2k_interleaving_implementation
53m 52s
Q2k interleaving implementation - x86/x64 SIMD CI #24326: Pull request #14373 synchronize by Srihari-mcw
20m 24s Srihari-mcw:q2k_interleaving_implementation
Srihari-mcw:q2k_interleaving_implementation
20m 24s
imatrix: add option to display importance score statistics for a given imatrix file CI #24325: Pull request #12718 synchronize by EAddario
51m 17s EAddario:imatrix
EAddario:imatrix
51m 17s
finetune: SGD optimizer, more CLI args CI #24324: Pull request #13873 synchronize by graehl
54m 10s graehl:finelayer
graehl:finelayer
54m 10s
server : (webui) let server send locally-defined default webui settings CI #24323: Pull request #14468 opened by woof-dog
54m 47s woof-dog:default-webui-settings
woof-dog:default-webui-settings
54m 47s
opencl: add GEGLU, REGLU, SWIGLU CI #24322: Pull request #14456 synchronize by lhez
55m 5s CodeLinaro:glu
CodeLinaro:glu
55m 5s
vulkan: Split large mul_mat_id to fit in shared memory CI #24321: Pull request #14451 synchronize by jeffbolznv
58m 34s jeffbolznv:mul_mat_id_splitting
jeffbolznv:mul_mat_id_splitting
58m 34s
model : add hunyuan moe CI #24320: Pull request #14425 synchronize by ngxson
1h 25m 25s ngxson:xsn/hunyuan-moe
ngxson:xsn/hunyuan-moe
1h 25m 25s
Add Conv2d for CPU (#14388) CI #24319: Commit 0a5a3b5 pushed by am17an
1h 9m 37s master
master
1h 9m 37s
model : add hunyuan moe CI #24318: Pull request #14425 synchronize by ngxson
6m 59s ngxson:xsn/hunyuan-moe
ngxson:xsn/hunyuan-moe
6m 59s
Granite Four CI #24317: Pull request #13550 synchronize by gabe-l-hart
1h 43m 26s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
1h 43m 26s
memory : correctly handle failure in apply() (#14438) CI #24316: Commit 745f11f pushed by ggerganov
1h 34m 45s master
master
1h 34m 45s
Add Conv2d for CPU CI #24315: Pull request #14388 synchronize by am17an
1h 12m 5s am17an:add_conv2d_cpu2
am17an:add_conv2d_cpu2
1h 12m 5s
Granite Four CI #24314: Pull request #13550 synchronize by gabe-l-hart
36m 28s gabe-l-hart:GraniteFour
gabe-l-hart:GraniteFour
36m 28s
Add Conv2d for CPU CI #24313: Pull request #14388 synchronize by am17an
14m 35s am17an:add_conv2d_cpu2
am17an:add_conv2d_cpu2
14m 35s
kv-cache : use ggml_set_rows CI #24312: Pull request #14285 synchronize by ggerganov
1h 38m 4s gg/kv-cache-use-set-rows
gg/kv-cache-use-set-rows
1h 38m 4s
metal : disable fast-math for some cpy kernels (#14460) CI #24311: Commit 5dd942d pushed by ggerganov
51m 16s master
master
51m 16s