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
2,917 workflow run results
2,917 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Refactor llama-model.cpp Build on RISCV Linux Machine by Cloud-V #3200: Pull request #16252 synchronize by pwilkin
31m 17s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
31m 17s
Refactor llama-model.cpp Build on RISCV Linux Machine by Cloud-V #3199: Pull request #16252 synchronize by pwilkin
19m 16s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
19m 16s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #3198: Pull request #16831 synchronize by pwilkin
39m 22s pwilkin:minimax-m2
pwilkin:minimax-m2
39m 22s
mtmd: refactor preprocessing + support max/min pixels Build on RISCV Linux Machine by Cloud-V #3197: Pull request #16878 synchronize by ngxson
39m 14s ngxson:xsn/mtmd-max-min-pixels
ngxson:xsn/mtmd-max-min-pixels
39m 14s
mtmd: refactor preprocessing + support max/min pixels Build on RISCV Linux Machine by Cloud-V #3196: Pull request #16878 synchronize by ngxson
25m 49s ngxson:xsn/mtmd-max-min-pixels
ngxson:xsn/mtmd-max-min-pixels
25m 49s
mtmd: refactor preprocessing + support max/min pixels Build on RISCV Linux Machine by Cloud-V #3195: Pull request #16878 synchronize by ngxson
3m 9s ngxson:xsn/mtmd-max-min-pixels
ngxson:xsn/mtmd-max-min-pixels
3m 9s
sync : ggml Build on RISCV Linux Machine by Cloud-V #3194: Pull request #16897 opened by ggerganov
4m 15s sync-ggml-25-10-31
sync-ggml-25-10-31
4m 15s
vulkan : refactor buffer handling in vk_op_f32 Build on RISCV Linux Machine by Cloud-V #3193: Pull request #16840 synchronize by Acly
4m 16s Acly:vulkan-op-subbuffer
Acly:vulkan-op-subbuffer
4m 16s
mtmd: refactor preprocessing + support max/min pixels Build on RISCV Linux Machine by Cloud-V #3192: Pull request #16878 synchronize by ngxson
6m 12s ngxson:xsn/mtmd-max-min-pixels
ngxson:xsn/mtmd-max-min-pixels
6m 12s
SYCL: optimized repeat_back kernel (3× fewer asm instructions, 2× faster)Feature/sycl repeat back opt Build on RISCV Linux Machine by Cloud-V #3191: Pull request #16869 synchronize by shani-f
17m 5s shani-f:feature/sycl-repeat-back-opt
shani-f:feature/sycl-repeat-back-opt
17m 5s
webui: auto-refresh /props on inference start to resync model metadata Build on RISCV Linux Machine by Cloud-V #3190: Pull request #16784 synchronize by ServeurpersoCom
17m 48s ServeurpersoCom:webui-props-auto-refresh
ServeurpersoCom:webui-props-auto-refresh
17m 48s
webui: auto-refresh /props on inference start to resync model metadata Build on RISCV Linux Machine by Cloud-V #3189: Pull request #16784 synchronize by ServeurpersoCom
8m 0s ServeurpersoCom:webui-props-auto-refresh
ServeurpersoCom:webui-props-auto-refresh
8m 0s
improve CUDA cpy memory bandwidth when copying transposed tensor Build on RISCV Linux Machine by Cloud-V #3188: Pull request #16841 synchronize by bssrdf
15m 46s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
15m 46s
mtmd: refactor preprocessing + support max/min pixels Build on RISCV Linux Machine by Cloud-V #3187: Pull request #16878 synchronize by ngxson
7m 35s ngxson:xsn/mtmd-max-min-pixels
ngxson:xsn/mtmd-max-min-pixels
7m 35s
webui: auto-refresh /props on inference start to resync model metadata Build on RISCV Linux Machine by Cloud-V #3186: Pull request #16784 synchronize by ServeurpersoCom
21m 29s ServeurpersoCom:webui-props-auto-refresh
ServeurpersoCom:webui-props-auto-refresh
21m 29s
webui: auto-refresh /props on inference start to resync model metadata Build on RISCV Linux Machine by Cloud-V #3185: Pull request #16784 reopened by ServeurpersoCom
14m 57s ServeurpersoCom:webui-props-auto-refresh
ServeurpersoCom:webui-props-auto-refresh
14m 57s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #3184: Pull request #16831 synchronize by pwilkin
10m 58s pwilkin:minimax-m2
pwilkin:minimax-m2
10m 58s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #3183: Pull request #16831 synchronize by pwilkin
8m 31s pwilkin:minimax-m2
pwilkin:minimax-m2
8m 31s
Refactor llama-model.cpp Build on RISCV Linux Machine by Cloud-V #3182: Pull request #16252 synchronize by pwilkin
3m 10s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
3m 10s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #3181: Pull request #16831 synchronize by pwilkin
12m 32s pwilkin:minimax-m2
pwilkin:minimax-m2
12m 32s
model: add Granite Hybrid nano Build on RISCV Linux Machine by Cloud-V #3180: Pull request #16896 opened by giuseppe
21m 37s giuseppe:granite-nano-models
giuseppe:granite-nano-models
21m 37s
CUDA: fuse rope + set_rows Build on RISCV Linux Machine by Cloud-V #3179: Pull request #16884 synchronize by am17an
7m 11s am17an:cuda-add-rope-fusion
am17an:cuda-add-rope-fusion
7m 11s
webui: add HTML/JS preview support to MarkdownContent with sandboxed iframe Build on RISCV Linux Machine by Cloud-V #3178: Pull request #16757 synchronize by ServeurpersoCom
30m 30s ServeurpersoCom:sandboxed-html-preview
ServeurpersoCom:sandboxed-html-preview
30m 30s
webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI Build on RISCV Linux Machine by Cloud-V #3177: Pull request #16618 synchronize by ServeurpersoCom
13m 11s ServeurpersoCom:harmony-toolcall-debug-option
ServeurpersoCom:harmony-toolcall-debug-option
13m 11s
CUDA: fuse rope + set_rows Build on RISCV Linux Machine by Cloud-V #3176: Pull request #16884 synchronize by am17an
9m 39s am17an:cuda-add-rope-fusion
am17an:cuda-add-rope-fusion
9m 39s
ProTip! You can narrow down the results and go further in time using created:<2025-10-31 or the other filters available.