Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
11,732 workflow runs
11,732 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CI CI #19678: Manually run by ggerganov
February 22, 2025 12:26 14m 17s gg/ci-fix-arm
gg/ci-fix-arm
February 22, 2025 12:26 14m 17s
ci : fix arm upload artifacts CI #19677: Pull request #12024 synchronize by ggerganov
February 22, 2025 11:55 44m 45s gg/ci-fix-arm
gg/ci-fix-arm
February 22, 2025 11:55 44m 45s
ci : fix arm upload artifacts CI #19676: Commit f385423 pushed by ggerganov
February 22, 2025 11:53 Failure gg/ci-fix-arm
gg/ci-fix-arm
February 22, 2025 11:53 Failure
CUDA: optimize FA for GQA + large batches (#12014) CI #19675: Commit 5fa07c2 pushed by JohannesGaessler
February 22, 2025 11:20 51m 34s master
master
February 22, 2025 11:20 51m 34s
llava: build clip image from pixels CI #19674: Pull request #11999 synchronize by ngxson
February 22, 2025 10:57 44m 6s tinglou:master
tinglou:master
February 22, 2025 10:57 44m 6s
ci : Build on Github-hosted arm64 runners (#12009) CI #19673: Commit 335eb04 pushed by ngxson
February 22, 2025 10:49 1h 0m 28s master
master
February 22, 2025 10:49 1h 0m 28s
server : disable Nagle's algorithm (#12020) CI #19672: Commit cf756d6 pushed by ngxson
February 22, 2025 10:46 56m 39s master
master
February 22, 2025 10:46 56m 39s
metal: Copy kernels for quant to F32 conversions (#10976). CI #19671: Pull request #12017 synchronize by ggerganov
February 22, 2025 09:51 33m 0s gcp:cpy_metal_quants
gcp:cpy_metal_quants
February 22, 2025 09:51 33m 0s
metal: Copy kernels for quant to F32 conversions (#10976). CI #19670: Pull request #12017 synchronize by ggerganov
February 22, 2025 09:49 2m 20s gcp:cpy_metal_quants
gcp:cpy_metal_quants
February 22, 2025 09:49 2m 20s
metal: Copy kernels for quant to F32 conversions (#10976). CI #19669: Pull request #12017 synchronize by ggerganov
February 22, 2025 09:48 1m 47s gcp:cpy_metal_quants
gcp:cpy_metal_quants
February 22, 2025 09:48 1m 47s
ggml-cpu: Support s390x SIMD Instruction Set CI #19668: Pull request #12019 synchronize by taronaeo
February 22, 2025 09:33 46m 9s taronaeo:master
taronaeo:master
February 22, 2025 09:33 46m 9s
server : disable Nagle's algorithm CI #19667: Pull request #12020 opened by ggerganov
February 22, 2025 08:59 38m 45s gg/server-disable-nagle
gg/server-disable-nagle
February 22, 2025 08:59 38m 45s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#12000) CI #19666: Commit d709084 pushed by JohannesGaessler
February 22, 2025 08:43 42m 19s master
master
February 22, 2025 08:43 42m 19s
llama.swiftui : add "Done" dismiss button to help view (#11998) CI #19665: Commit de8b5a3 pushed by danbev
February 22, 2025 05:33 39m 6s master
master
February 22, 2025 05:33 39m 6s
vulkan: improve im2col and RDNA1 performance CI #19664: Pull request #11826 synchronize by daniandtheweb
February 22, 2025 03:30 34m 48s daniandtheweb:vk-shader-optimizations-1
daniandtheweb:vk-shader-optimizations-1
February 22, 2025 03:30 34m 48s
vulkan: improve im2col and RDNA1 performance CI #19663: Pull request #11826 synchronize by daniandtheweb
February 22, 2025 02:56 34m 37s daniandtheweb:vk-shader-optimizations-1
daniandtheweb:vk-shader-optimizations-1
February 22, 2025 02:56 34m 37s
ggml-qnn: fix a minior typo in internal doc CI #19662: Pull request #12018 opened by zhouwg
February 22, 2025 02:26 22m 21s kantv-ai:finetune_mulmat_2
kantv-ai:finetune_mulmat_2
February 22, 2025 02:26 22m 21s
vulkan: improve im2col and RDNA1 performance CI #19661: Pull request #11826 synchronize by daniandtheweb
February 22, 2025 01:33 34m 51s daniandtheweb:vk-shader-optimizations-1
daniandtheweb:vk-shader-optimizations-1
February 22, 2025 01:33 34m 51s
metal: Copy kernels for quant to F32 conversions (#10976). CI #19660: Pull request #12017 synchronize by gcp
February 22, 2025 00:09 33m 15s gcp:cpy_metal_quants
gcp:cpy_metal_quants
February 22, 2025 00:09 33m 15s
metal: Copy kernels for quant to F32 conversions (#10976). CI #19659: Pull request #12017 opened by gcp
February 22, 2025 00:03 35m 56s gcp:cpy_metal_quants
gcp:cpy_metal_quants
February 22, 2025 00:03 35m 56s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) CI #19658: Pull request #12000 synchronize by gcp
February 21, 2025 23:52 34m 23s gcp:cpy_cuda_quants
gcp:cpy_cuda_quants
February 21, 2025 23:52 34m 23s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) CI #19657: Pull request #12000 synchronize by gcp
February 21, 2025 23:14 Action required gcp:cpy_cuda_quants
gcp:cpy_cuda_quants
February 21, 2025 23:14 Action required
vulkan: matmul dequantization improvements CI #19656: Pull request #12015 opened by netrunnereve
February 21, 2025 22:35 39m 50s netrunnereve:vulkan_mm
netrunnereve:vulkan_mm
February 21, 2025 22:35 39m 50s
CUDA: optimize FA for GQA + large batches CI #19655: Pull request #12014 opened by JohannesGaessler
February 21, 2025 22:19 46m 7s JohannesGaessler:cuda-fa-mma-23
JohannesGaessler:cuda-fa-mma-23
February 21, 2025 22:19 46m 7s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) CI #19654: Pull request #12000 synchronize by gcp
February 21, 2025 21:51 Action required gcp:cpy_cuda_quants
gcp:cpy_cuda_quants
February 21, 2025 21:51 Action required