Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
8,146 workflow run results
8,146 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : add high-throughput mode CI #24543: Pull request #14363 synchronize by ggerganov
1h 3m 54s gg/llama-high-throughput
gg/llama-high-throughput
1h 3m 54s
llama : add high-throughput mode CI #24542: Pull request #14363 synchronize by ggerganov
12m 32s gg/llama-high-throughput
gg/llama-high-throughput
12m 32s
server: Add ability to mount server at prefix CI #24541: Pull request #14544 synchronize by oluwandabira
1h 5m 30s oluwandabira:prefix
oluwandabira:prefix
1h 5m 30s
llama : add high-throughput mode CI #24539: Pull request #14363 synchronize by ggerganov
1h 3m 58s gg/llama-high-throughput
gg/llama-high-throughput
1h 3m 58s
CUDA: add bilinear interpolation for upscale CI #24536: Pull request #14563 opened by am17an
1h 12m 31s am17an:cuda_upscale_bilinear
am17an:cuda_upscale_bilinear
1h 12m 31s
SYCL: Initial set_rows kernel implementation CI #24535: Pull request #14562 opened by qnixsynapse
1h 33m 59s sycl/set_rows
sycl/set_rows
1h 33m 59s
llama : add high-throughput mode CI #24534: Pull request #14363 synchronize by ggerganov
1h 9m 52s gg/llama-high-throughput
gg/llama-high-throughput
1h 9m 52s
llama : add high-throughput mode CI #24533: Pull request #14363 synchronize by ggerganov
13m 37s gg/llama-high-throughput
gg/llama-high-throughput
13m 37s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #24532: Pull request #12326 synchronize by jeffzhou2000
1h 14m 4s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
1h 14m 4s
llama : add high-throughput mode CI #24531: Pull request #14363 synchronize by ggerganov
11m 45s gg/llama-high-throughput
gg/llama-high-throughput
11m 45s
musa: fix build warnings (unused variable) CI #24530: Pull request #14561 opened by yeahdongcn
1h 25m 29s makllama:xd/warn
makllama:xd/warn
1h 25m 29s
llama : reuse compute graphs CI #24529: Pull request #14482 synchronize by ggerganov
1h 10m 21s gg/llama-reuse-graphs
gg/llama-reuse-graphs
1h 10m 21s
opencl: add set_rows for f16 and f32 CI #24528: Pull request #14547 synchronize by lhez
1h 6m 25s CodeLinaro:set-rows-f16-f32
CodeLinaro:set-rows-f16-f32
1h 6m 25s
model : jina-embeddings-v3 support CI #24527: Pull request #13693 synchronize by CISC
1h 4m 46s cisc/jina-embeddings-v3
cisc/jina-embeddings-v3
1h 4m 46s
server: Add ability to mount server at prefix CI #24526: Pull request #14544 synchronize by oluwandabira
1h 11m 6s oluwandabira:prefix
oluwandabira:prefix
1h 11m 6s
vulkan: optimizations for deepseek prompt processing CI #24525: Pull request #14555 opened by jeffbolznv
1h 6m 36s jeffbolznv:deepseek_opts2
jeffbolznv:deepseek_opts2
1h 6m 36s
model : jina-embeddings-v3 support CI #24524: Pull request #13693 synchronize by CISC
1h 5m 31s cisc/jina-embeddings-v3
cisc/jina-embeddings-v3
1h 5m 31s
vulkan: optimize flash attention split_k_reduce CI #24523: Pull request #14554 opened by jeffbolznv
1h 8m 1s jeffbolznv:fa_split_k_opts
jeffbolznv:fa_split_k_opts
1h 8m 1s
ggml: Add initial WebGPU backend CI #24522: Pull request #14521 synchronize by reeselevine
1h 7m 26s reeselevine:webgpu
reeselevine:webgpu
1h 7m 26s
llama : add high-throughput mode CI #24521: Pull request #14363 synchronize by ggerganov
1h 4m 42s gg/llama-high-throughput
gg/llama-high-throughput
1h 4m 42s
llama : add high-throughput mode CI #24520: Pull request #14363 synchronize by ggerganov
17m 8s gg/llama-high-throughput
gg/llama-high-throughput
17m 8s
ggml: Add initial WebGPU backend CI #24519: Pull request #14521 synchronize by reeselevine
1h 5m 2s reeselevine:webgpu
reeselevine:webgpu
1h 5m 2s
model : jina-embeddings-v3 support CI #24518: Pull request #13693 synchronize by CISC
1h 9m 23s cisc/jina-embeddings-v3
cisc/jina-embeddings-v3
1h 9m 23s
CUDA: add set rows for f32 and f16 CI #24517: Pull request #14551 synchronize by am17an
1h 3m 28s am17an:cuda_set_rows
am17an:cuda_set_rows
1h 3m 28s
model : jina-embeddings-v3 support CI #24516: Pull request #13693 synchronize by CISC
28s cisc/jina-embeddings-v3
cisc/jina-embeddings-v3
28s