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
816 workflow run results
816 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #759: Pull request #15818 synchronize by ericcurtin
8m 19s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
8m 19s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #758: Pull request #15818 synchronize by ericcurtin
4m 52s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
4m 52s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #757: Pull request #15818 synchronize by ericcurtin
4m 52s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
4m 52s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #756: Pull request #15818 synchronize by ericcurtin
7m 4s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
7m 4s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #755: Pull request #15818 synchronize by ericcurtin
4m 51s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
4m 51s
Implement --log-colors with always/never/auto Build on RISCV Linux Machine by Cloud-V #754: Pull request #15792 synchronize by ericcurtin
6m 1s auto-color
auto-color
6m 1s
convert : use reflinks for faster conversion Build on RISCV Linux Machine by Cloud-V #753: Pull request #15727 synchronize by compilade
4m 50s compilade/convert-reflinks
compilade/convert-reflinks
4m 50s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #752: Pull request #15818 synchronize by ericcurtin
4m 54s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
4m 54s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #751: Pull request #15818 synchronize by ericcurtin
9m 58s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
9m 58s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #750: Pull request #15818 synchronize by ericcurtin
5m 50s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
5m 50s
Implement --log-colors with always/never/auto Build on RISCV Linux Machine by Cloud-V #749: Pull request #15792 synchronize by ericcurtin
9m 20s auto-color
auto-color
9m 20s
Implement --log-colors with always/never/auto Build on RISCV Linux Machine by Cloud-V #748: Pull request #15792 synchronize by ericcurtin
6m 20s auto-color
auto-color
6m 20s
Rewrite llama-run to use llama-server Build on RISCV Linux Machine by Cloud-V #747: Pull request #15818 opened by ericcurtin
4m 51s rewrite-llama-run-to-be-llama-server-based
rewrite-llama-run-to-be-llama-server-based
4m 51s
Implement --log-colors with always/never/auto Build on RISCV Linux Machine by Cloud-V #746: Pull request #15792 synchronize by ericcurtin
21m 42s auto-color
auto-color
21m 42s
Implement --log-colors with always/never/auto Build on RISCV Linux Machine by Cloud-V #745: Pull request #15792 synchronize by ericcurtin
18m 33s auto-color
auto-color
18m 33s
kleidiai: generalize compute_forward_kv_cache to compute_forward_fp16 Build on RISCV Linux Machine by Cloud-V #744: Pull request #15817 opened by chaxu01
5m 3s chaxu01:feature/generic-kv-cache
chaxu01:feature/generic-kv-cache
5m 3s
CUDA: fastdiv, launch bounds for mmvq + q8_1 quant Build on RISCV Linux Machine by Cloud-V #743: Pull request #15802 synchronize by JohannesGaessler
4m 53s JohannesGaessler:cuda-mmvq-fastdiv-3
JohannesGaessler:cuda-mmvq-fastdiv-3
4m 53s
[WIP] Add a --cli option to llama-server that also forks a linenoise.cpp based cli process on launch of llama-server (use existing linenoise.cpp in the repo). This forked process acts as a client that speaks to the /chat/completions API in llama-server. Ctrl... Build on RISCV Linux Machine by Cloud-V #742: Pull request #15816 opened by Copilot AI
5m 3s copilot/fix-08a581ef-1482-4dea-8494-f9f717e8982a
copilot/fix-08a581ef-1482-4dea-8494-f9f717e8982a
5m 3s
ggml-cpu: fixes instability in NNPA Vector Intrinsics Build on RISCV Linux Machine by Cloud-V #741: Pull request #15739 synchronize by taronaeo
21m 15s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
21m 15s
ggml-cpu: fixes instability in NNPA Vector Intrinsics Build on RISCV Linux Machine by Cloud-V #740: Pull request #15739 synchronize by taronaeo
21m 34s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
21m 34s
ggml : split graph allocations according to backend max buffer size Build on RISCV Linux Machine by Cloud-V #739: Pull request #15815 opened by Acly
35m 16s Acly:gallocr-max-size
Acly:gallocr-max-size
35m 16s
ggml-cpu: fixes instability in NNPA Vector Intrinsics Build on RISCV Linux Machine by Cloud-V #738: Pull request #15739 synchronize by taronaeo
18m 28s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
18m 28s
ggml-cpu: fixes instability in NNPA Vector Intrinsics Build on RISCV Linux Machine by Cloud-V #737: Pull request #15739 synchronize by taronaeo
14m 3s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
14m 3s
ggml-cpu: fixes instability in NNPA Vector Intrinsics Build on RISCV Linux Machine by Cloud-V #736: Pull request #15739 synchronize by taronaeo
15m 21s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
15m 21s
ggml-cpu: fixes instability in NNPA Vector Intrinsics Build on RISCV Linux Machine by Cloud-V #735: Pull request #15739 synchronize by taronaeo
10m 25s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
10m 25s