Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
9,208 workflow run results
9,208 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

chat : Avoid partial reasoning tags in response content CI #25854: Pull request #15149 synchronize by p1-0tr
59m 27s p1-0tr:ps-fix-reasoning-tags-in-content
p1-0tr:ps-fix-reasoning-tags-in-content
59m 27s
chat : Avoid partial reasoning tags in response content CI #25853: Pull request #15149 opened by p1-0tr
32m 3s p1-0tr:ps-fix-reasoning-tags-in-content
p1-0tr:ps-fix-reasoning-tags-in-content
32m 3s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 (#15131) CI #25852: Commit 1d72c84 pushed by JohannesGaessler
1h 2m 11s master
master
1h 2m 11s
Fix MinicpmV model converter and clip to avoid using hardcode. CI #25851: Pull request #14750 synchronize by gryffindor-rr
1h 3m 15s gryffindor-rr:master
gryffindor-rr:master
1h 3m 15s
CUDA: Optimize reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n CI #25850: Pull request #15132 synchronize by ORippler
1h 12m 24s ORippler:osimons/optimize_reduce_rows_f32
ORippler:osimons/optimize_reduce_rows_f32
1h 12m 24s
CUDA: Optimize reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n CI #25848: Pull request #15132 synchronize by ORippler
33m 41s ORippler:osimons/optimize_reduce_rows_f32
ORippler:osimons/optimize_reduce_rows_f32
33m 41s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 CI #25847: Pull request #15131 synchronize by JohannesGaessler
1h 1m 30s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
1h 1m 30s
ggml: SVE support for exponential functions CI #25846: Pull request #15145 opened by s-goto-11
1h 7m 54s s-goto-11:feature-exp-sve-0806pr
s-goto-11:feature-exp-sve-0806pr
1h 7m 54s
ggml: aarch64: Implement SVE F16 kernels for vector functions CI #25845: Pull request #15115 synchronize by Vithulep
1h 1m 11s Vithulep:Vec_dot_fp16_Sve_implementation
Vithulep:Vec_dot_fp16_Sve_implementation
1h 1m 11s
finetune: SGD optimizer, more CLI args CI #25844: Pull request #13873 synchronize by graehl
1h 24m 58s graehl:finelayer
graehl:finelayer
1h 24m 58s
model : add reasoning/tool parsing to Llama 3.x Nemotron CI #25841: Pull request #15083 synchronize by aldehir
1h 0m 14s aldehir:model/llama-nemotron-reasoning
aldehir:model/llama-nemotron-reasoning
1h 0m 14s
mtmd: server: Support multimodal data prompt in /completions and /embeddings endpoint of server CI #25840: Pull request #15108 synchronize by 65a
1h 10m 6s 65a:master
65a:master
1h 10m 6s
mtmd: server: Support multimodal data prompt in /completions and /embeddings endpoint of server CI #25839: Pull request #15108 synchronize by 65a
4m 3s 65a:master
65a:master
4m 3s
Add T5Gemma support #14940 CI #25838: Pull request #15123 synchronize by baonudesifeizhai
1h 16m 2s baonudesifeizhai:t5gemma-support
baonudesifeizhai:t5gemma-support
1h 16m 2s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 CI #25837: Pull request #15131 synchronize by JohannesGaessler
59m 37s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
59m 37s
ggml: Add basic SET_ROWS support in WebGPU (#15137) CI #25835: Commit 5fd160b pushed by reeselevine
1h 1m 9s master
master
1h 1m 9s
OpenCL: allow mixed f16/f32 add CI #25834: Pull request #15140 opened by rmatif
1h 7m 15s rmatif:opencl-mixed-add
rmatif:opencl-mixed-add
1h 7m 15s
fix profiling crash (#15072) CI #25833: Commit 756cfea pushed by max-krasnyansky
1h 2m 38s master
master
1h 2m 38s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 CI #25832: Pull request #15131 synchronize by JohannesGaessler
1h 8m 14s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
1h 8m 14s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 CI #25831: Pull request #15131 synchronize by JohannesGaessler
12m 45s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
12m 45s
gguf-py : add Numpy MXFP4 de/quantization support CI #25830: Pull request #15111 synchronize by compilade
1h 15m 15s compilade/gguf-py-mxfp4
compilade/gguf-py-mxfp4
1h 15m 15s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 CI #25829: Pull request #15131 synchronize by JohannesGaessler
19m 36s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
19m 36s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 CI #25828: Pull request #15131 synchronize by JohannesGaessler
6m 38s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
6m 38s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 CI #25827: Pull request #15131 synchronize by JohannesGaessler
9m 1s JohannesGaessler:cuda-mmf-3
JohannesGaessler:cuda-mmf-3
9m 1s
ggml: Add basic SET_ROWS support in WebGPU CI #25826: Pull request #15137 opened by reeselevine
1h 6m 24s reeselevine:master
reeselevine:master
1h 6m 24s