Skip to content

Actions: InfernalDread/llama.cpp

Actions

CI (android)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-android.yml
37 workflow runs
37 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
github: mention --log-file in issue templates (#23277) CI (android) #37: Commit a807867 pushed by InfernalDread
49m 56s master
master
49m 56s
cmake : do not install conversion script (#23204) CI (android) #36: Commit e0de4c2 pushed by InfernalDread
32m 32s master
master
32m 32s
model : support Gemma4_26B_A4B_NVFP4 (#22804) CI (android) #35: Commit 9f5f0e6 pushed by InfernalDread
37m 15s master
master
37m 15s
model: Support sarashina2.2-vision-3b model (#22103) CI (android) #34: Commit 44dbe8c pushed by InfernalDread
56m 32s master
master
56m 32s
ggml : use CL_DEVICE_GLOBAL_MEM_SIZE as memory estimate for OpenCL … CI (android) #33: Commit 2ca1161 pushed by InfernalDread
22m 23s master
master
22m 23s
Hexagon: Process M-tail rows on HMX instead of HVX (#22724) CI (android) #32: Commit bbeb89d pushed by InfernalDread
41m 54s master
master
41m 54s
kleidiai : update to v1.24.0 and use release archive (#22549) CI (android) #31: Commit eff0670 pushed by InfernalDread
42m 11s master
master
42m 11s
fix: CUDA device PCI bus ID de-dupe OOMing (ignoring other 3 gpus ent… CI (android) #30: Commit d05fe1d pushed by InfernalDread
45m 1s master
master
45m 1s
llama-quant : fix --tensor-type when default qtype is overriden (… CI (android) #29: Commit b97ebdc pushed by InfernalDread
29m 46s master
master
29m 46s
common : do not pass prompt tokens to reasoning budget sampler (#22488) CI (android) #28: Commit d775992 pushed by InfernalDread
13m 21s master
master
13m 21s
ggml-cuda: Repost of 21896: Blackwell native NVFP4 support (#22196) CI (android) #27: Commit fc2b005 pushed by InfernalDread
32m 13s master
master
32m 13s
spec : fix vocab compat checks (#22358) CI (android) #26: Commit 98dc141 pushed by InfernalDread
47m 17s master
master
47m 17s
ggml-webgpu: enable FLASH_ATTN_EXT on browser without subgroup matrix… CI (android) #25: Commit 13d36cf pushed by InfernalDread
46m 0s master
master
46m 0s
Enable testing on Snapdragon devices (#21051) CI (android) #24: Commit 187a456 pushed by InfernalDread
1h 20m 46s master
master
1h 20m 46s
turboquant_kv_cache_updated_v12 again CI (android) #23: Pull request #35 opened by InfernalDread
34m 13s ggml-org:master
ggml-org:master
34m 13s
server : convert_anthropic_to_oai: also copy chat_template_kwargs (#2… CI (android) #22: Commit 185cbff pushed by InfernalDread
1h 22m 22s master
master
1h 22m 22s
[WebGPU] Implement async tensor api and event api (#22099) CI (android) #21: Commit 0d0764d pushed by InfernalDread
31m 23s master
master
31m 23s
spec : reset i_last when low acceptance streak occurs (#22168) CI (android) #20: Commit 72d693e pushed by InfernalDread
45m 18s master
master
45m 18s
common/autoparser : allow space after tool call (#22073) CI (android) #19: Commit d5b780a pushed by InfernalDread
20m 28s master
master
20m 28s
turboquant_kv_cache_updated_v9 CI (android) #18: Pull request #31 opened by InfernalDread
48m 49s ggml-org:master
ggml-org:master
48m 49s
ggml-webgpu: fix compiler warnings and refactor FlashAttention encodi… CI (android) #17: Commit 45cac7c pushed by InfernalDread
53m 40s master
master
53m 40s
model: using single llm_build per arch (#21970) CI (android) #16: Commit 4fbdabd pushed by InfernalDread
41m 47s master
master
41m 47s
vulkan: optimize im2col (#21713) CI (android) #15: Commit b3d7587 pushed by InfernalDread
1h 3m 5s master
master
1h 3m 5s
ggml : remove ggml-ext.h (#21869) CI (android) #14: Commit fae3a28 pushed by InfernalDread
57m 15s master
master
57m 15s
common/gemma4 : handle parsing edge cases (#21760) CI (android) #13: Commit e21cdc1 pushed by InfernalDread
17m 36s master
master
17m 36s