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
707 workflow run results
707 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free Build on RISCV Linux Machine by Cloud-V #804: Pull request #15839 synchronize by taronaeo
4m 54s taronaeo:fix/15414-llama-set-rows
taronaeo:fix/15414-llama-set-rows
4m 54s
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free Build on RISCV Linux Machine by Cloud-V #803: Pull request #15839 synchronize by taronaeo
4m 57s taronaeo:fix/15414-llama-set-rows
taronaeo:fix/15414-llama-set-rows
4m 57s
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free Build on RISCV Linux Machine by Cloud-V #802: Pull request #15839 opened by taronaeo
4m 54s taronaeo:fix/15414-llama-set-rows
taronaeo:fix/15414-llama-set-rows
4m 54s
llguidance : use attrs to determine special tokens Build on RISCV Linux Machine by Cloud-V #801: Pull request #15837 synchronize by dstoc
8m 54s dstoc:llguidance-special-tokens
dstoc:llguidance-special-tokens
8m 54s
webgpu : fix build on emscripten Build on RISCV Linux Machine by Cloud-V #799: Pull request #15826 synchronize by ngxson
32m 56s ngxson:xsn/emscripten_webgpu
ngxson:xsn/emscripten_webgpu
32m 56s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error Build on RISCV Linux Machine by Cloud-V #798: Pull request #15550 synchronize by EAddario
43m 35s EAddario:quantize
EAddario:quantize
43m 35s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Build on RISCV Linux Machine by Cloud-V #797: Pull request #14891 synchronize by EAddario
19m 33s EAddario:imatrix
EAddario:imatrix
19m 33s
server : speed up tests Build on RISCV Linux Machine by Cloud-V #796: Pull request #15836 synchronize by ngxson
10m 42s xsn/server_speedup_test
xsn/server_speedup_test
10m 42s
server : speed up tests Build on RISCV Linux Machine by Cloud-V #795: Pull request #15836 synchronize by ngxson
18m 43s xsn/server_speedup_test
xsn/server_speedup_test
18m 43s
server : speed up tests Build on RISCV Linux Machine by Cloud-V #794: Pull request #15836 synchronize by ngxson
12m 11s xsn/server_speedup_test
xsn/server_speedup_test
12m 11s
server : speed up tests Build on RISCV Linux Machine by Cloud-V #793: Pull request #15836 opened by ngxson
11m 18s xsn/server_speedup_test
xsn/server_speedup_test
11m 18s
batched-bench : fix llama_synchronize usage during prompt processing Build on RISCV Linux Machine by Cloud-V #792: Pull request #15835 opened by ggerganov
15m 26s gg/batched-bench-fix-synchronize
gg/batched-bench-fix-synchronize
15m 26s
ggml-cpu: document use of "free" memory [no ci] Build on RISCV Linux Machine by Cloud-V #791: Pull request #15834 opened by JohannesGaessler
3m 4s JohannesGaessler:ggml-cpu-fix-free-memory
JohannesGaessler:ggml-cpu-fix-free-memory
3m 4s
server : implement prompt processing progress report in stream mode Build on RISCV Linux Machine by Cloud-V #790: Pull request #15827 synchronize by ngxson
3m 3s xsn/server_progress_api
xsn/server_progress_api
3m 3s
server : implement prompt processing progress report in stream mode Build on RISCV Linux Machine by Cloud-V #789: Pull request #15827 synchronize by ngxson
4m 54s xsn/server_progress_api
xsn/server_progress_api
4m 54s
server : implement prompt processing progress report in stream mode Build on RISCV Linux Machine by Cloud-V #788: Pull request #15827 synchronize by ngxson
4m 53s xsn/server_progress_api
xsn/server_progress_api
4m 53s
vulkan: add mul_mat variant for embedded gpus Build on RISCV Linux Machine by Cloud-V #787: Pull request #15800 synchronize by rmatif
4m 57s rmatif:vk-mulmat-embed
rmatif:vk-mulmat-embed
4m 57s
metal : make the backend async Build on RISCV Linux Machine by Cloud-V #786: Pull request #15832 opened by ggerganov
4m 57s gg/metal-async
gg/metal-async
4m 57s
json : support enum values within allOf Build on RISCV Linux Machine by Cloud-V #785: Pull request #15830 opened by aldehir
6m 38s aldehir:fix-allOf-enum
aldehir:fix-allOf-enum
6m 38s
server : implement prompt processing progress report in stream mode Build on RISCV Linux Machine by Cloud-V #783: Pull request #15827 synchronize by ngxson
11m 7s xsn/server_progress_api
xsn/server_progress_api
11m 7s
requirements : update transformers/torch for Embedding Gemma Build on RISCV Linux Machine by Cloud-V #782: Pull request #15828 opened by danbev
11m 6s danbev:requirements-embeddinggemma-conversion
danbev:requirements-embeddinggemma-conversion
11m 6s
Deepseek V3.1 native tool calling support (OpenAI Style) Build on RISCV Linux Machine by Cloud-V #781: Pull request #15533 synchronize by createthis
20m 18s createthis:deepseek_3_1_thinking_mode
createthis:deepseek_3_1_thinking_mode
20m 18s
server : implement prompt processing progress report in stream mode Build on RISCV Linux Machine by Cloud-V #780: Pull request #15827 opened by ngxson
24m 45s xsn/server_progress_api
xsn/server_progress_api
24m 45s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #779: Pull request #14839 synchronize by allozaur
20m 22s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
20m 22s
webgpu : fix build on emscripten Build on RISCV Linux Machine by Cloud-V #778: Pull request #15826 synchronize by ngxson
5m 53s ngxson:xsn/emscripten_webgpu
ngxson:xsn/emscripten_webgpu
5m 53s