Skip to content

Actions: ggml-org/llama.cpp

Actions

Build on RISCV Linux Machine by Cloud-V

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-riscv-native.yml
930 workflow run results
930 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA: larger SRAM reads for tile FA, AMD FP16 dot Build on RISCV Linux Machine by Cloud-V #1015: Pull request #15927 opened by JohannesGaessler
29m 25s JohannesGaessler:cuda-fa-tile-mem-pattern-4
JohannesGaessler:cuda-fa-tile-mem-pattern-4
29m 25s
Add model to header title with mouseover Build on RISCV Linux Machine by Cloud-V #1014: Pull request #15787 synchronize by pudepiedj
3m 5s pudepiedj:feat/header-show-model-name
pudepiedj:feat/header-show-model-name
3m 5s
Add model to header title with mouseover Build on RISCV Linux Machine by Cloud-V #1013: Pull request #15787 synchronize by pudepiedj
8m 54s pudepiedj:feat/header-show-model-name
pudepiedj:feat/header-show-model-name
8m 54s
Add model to header title with mouseover Build on RISCV Linux Machine by Cloud-V #1012: Pull request #15787 synchronize by pudepiedj
10m 33s pudepiedj:feat/header-show-model-name
pudepiedj:feat/header-show-model-name
10m 33s
Extend the support of T5 models with different encoder-decoder layers Build on RISCV Linux Machine by Cloud-V #1011: Pull request #15909 synchronize by DamonFool
1h 11m 8s DamonFool:t5-enhancement
DamonFool:t5-enhancement
1h 11m 8s
Feat: Apertus model implementation Build on RISCV Linux Machine by Cloud-V #1010: Pull request #15852 synchronize by pwilkin
1h 2m 57s pwilkin:apertus-implementation
pwilkin:apertus-implementation
1h 2m 57s
CUDA: some micro-optimizations in mmf.cuh for mul_mat_id Build on RISCV Linux Machine by Cloud-V #1009: Pull request #15926 opened by am17an
17m 58s am17an:mmf_opt_cuda
am17an:mmf_opt_cuda
17m 58s
devops: add s390x & ppc64le CI Build on RISCV Linux Machine by Cloud-V #1008: Pull request #15925 synchronize by taronaeo
13m 56s taronaeo:feat/s390x-ci
taronaeo:feat/s390x-ci
13m 56s
metal : make the backend async v2 Build on RISCV Linux Machine by Cloud-V #1007: Pull request #15906 synchronize by ggerganov
9m 16s gg/metal-async-v2
gg/metal-async-v2
9m 16s
devops: add s390x & ppc64le CI Build on RISCV Linux Machine by Cloud-V #1006: Pull request #15925 synchronize by taronaeo
8m 24s taronaeo:feat/s390x-ci
taronaeo:feat/s390x-ci
8m 24s
Extend the support of T5 models with different encoder-decoder layers Build on RISCV Linux Machine by Cloud-V #1005: Pull request #15909 synchronize by DamonFool
54m 42s DamonFool:t5-enhancement
DamonFool:t5-enhancement
54m 42s
metal : make the backend async v2 Build on RISCV Linux Machine by Cloud-V #1004: Pull request #15906 synchronize by ggerganov
8m 48s gg/metal-async-v2
gg/metal-async-v2
8m 48s
devops: add s390x & ppc64le CI Build on RISCV Linux Machine by Cloud-V #1003: Pull request #15925 opened by taronaeo
6m 32s taronaeo:feat/s390x-ci
taronaeo:feat/s390x-ci
6m 32s
ci : add caching for ROCm installation in release workflow Build on RISCV Linux Machine by Cloud-V #1002: Pull request #15924 opened by danbev
16m 31s danbev:ci-cache-rocm-installation-release-workflow
danbev:ci-cache-rocm-installation-release-workflow
16m 31s
ggml-cpu : add check for ARM MATMUL_INT8/i8mm support Build on RISCV Linux Machine by Cloud-V #1000: Pull request #15922 opened by danbev
41m 46s danbev:ggml-cpu-arm-i8mm-feature-issue
danbev:ggml-cpu-arm-i8mm-feature-issue
41m 46s
Add docker protocol support for llama-server model loading Build on RISCV Linux Machine by Cloud-V #999: Pull request #15790 synchronize by ericcurtin
44m 49s docker-pull-functionality
docker-pull-functionality
44m 49s
graph : support non-contiguous Q in build_attn_mha Build on RISCV Linux Machine by Cloud-V #998: Pull request #15908 synchronize by CISC
10m 10s cisc/non-contiguous-q-build-attn-mha
cisc/non-contiguous-q-build-attn-mha
10m 10s
Add model to header title with mouseover Build on RISCV Linux Machine by Cloud-V #996: Pull request #15787 synchronize by pudepiedj
21m 24s pudepiedj:feat/header-show-model-name
pudepiedj:feat/header-show-model-name
21m 24s
ggml-cpu : fix padding in ggml_timestep_embedding Build on RISCV Linux Machine by Cloud-V #994: Pull request #15917 opened by danbev
26m 7s danbev:ggml-timestep-embedding-padding
danbev:ggml-timestep-embedding-padding
26m 7s
llama : bump max seq limit from 64 to 256 Build on RISCV Linux Machine by Cloud-V #993: Pull request #15916 opened by ggerganov
21m 32s gg/llama-bump-max-seq
gg/llama-bump-max-seq
21m 32s
devops: add s390x containers Build on RISCV Linux Machine by Cloud-V #992: Pull request #15915 opened by taronaeo
11m 7s taronaeo:feat/s390x-docker
taronaeo:feat/s390x-docker
11m 7s
Extend the support of T5 models with different encoder-decoder layers Build on RISCV Linux Machine by Cloud-V #991: Pull request #15909 synchronize by DamonFool
3h 4m 44s DamonFool:t5-enhancement
DamonFool:t5-enhancement
3h 4m 44s
Extend the support of T5 models with different encoder-decoder layers Build on RISCV Linux Machine by Cloud-V #990: Pull request #15909 synchronize by DamonFool
2h 56m 26s DamonFool:t5-enhancement
DamonFool:t5-enhancement
2h 56m 26s
Extend the support of T5 models with different encoder-decoder layers Build on RISCV Linux Machine by Cloud-V #989: Pull request #15909 synchronize by DamonFool
2h 54m 37s DamonFool:t5-enhancement
DamonFool:t5-enhancement
2h 54m 37s
Extend the support of T5 models with different encoder-decoder layers Build on RISCV Linux Machine by Cloud-V #988: Pull request #15909 synchronize by DamonFool
2h 47m 33s DamonFool:t5-enhancement
DamonFool:t5-enhancement
2h 47m 33s