Skip to content

Actions: ggml-org/llama.cpp

Actions

CI (AMD)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-amd.yml
48 workflow run results
48 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml webgpu: profiling, CI updates, reworking of command submission (… CI (AMD) #48: Commit 74b8fc1 pushed by reeselevine
31m 19s master
master
31m 19s
llama : support LiquidAI LFM2-MoE hybrid model (#16464) CI (AMD) #47: Commit aeaf8a3 pushed by CISC
44m 29s master
master
44m 29s
server : add /v1/health endpoint (#16461) CI (AMD) #46: Commit df1b612 pushed by ggerganov
44m 11s master
master
44m 11s
presets : fix pooling param for embedding models (#16455) CI (AMD) #45: Commit ef4c5b8 pushed by ggerganov
1h 20m 49s master
master
1h 20m 49s
memory : use sequential equal splits for recurrent modules (#16442) CI (AMD) #44: Commit 0123ff3 pushed by ggerganov
2h 47m 18s master
master
2h 47m 18s
metal : add support for non-padded FA KV (#16148) CI (AMD) #43: Commit 0a319bb pushed by ggerganov
2h 2m 21s master
master
2h 2m 21s
tests : add -INF blocks to the KQ mask in the FA tests (#16380) CI (AMD) #42: Commit 1d6092f pushed by ggerganov
1h 17m 7s master
master
1h 17m 7s
metal : various optimizations + refactoring (#16446) CI (AMD) #41: Commit 8ae32dc pushed by ggerganov
45m 44s master
master
45m 44s
llama : add --no-host to disable host buffers (#16310) CI (AMD) #40: Commit 3df2244 pushed by slaren
46m 28s master
master
46m 28s
chat : Granite Docling stopping (#16438) CI (AMD) #39: Commit c08002a pushed by CISC
44m 3s master
master
44m 3s
ggml : fix unaligned access in AMX code (#16315) CI (AMD) #38: Commit a23b9bd pushed by ggerganov
44m 16s master
master
44m 16s
ggml-cpu : fix leftover handling in ggml_vec_scale_f32 for SVE (#16443) CI (AMD) #37: Commit a80ff18 pushed by danbev
44m 12s master
master
44m 12s
model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206) CI (AMD) #36: Commit ca71fb9 pushed by CISC
44m 43s master
master
44m 43s
ggml webgpu: actually add softmax, fix rms_norm offset (#16400) CI (AMD) #35: Commit 3526657 pushed by reeselevine
45m 41s master
master
45m 41s
vulkan: use a more appropriate amount of threads when generating shad… CI (AMD) #34: Commit 86df2c9 pushed by 0cc4m
51m 22s master
master
51m 22s
rpc : check src buffer when copying tensor (#16421) CI (AMD) #33: Commit f392839 pushed by rgerganov
43m 12s master
master
43m 12s
rpc : add support for multiple devices (#16276) CI (AMD) #32: Commit 898acba pushed by rgerganov
1h 17m 1s master
master
1h 17m 1s
vulkan : incremental shader builds (#16341) CI (AMD) #31: Commit e29acf7 pushed by 0cc4m
45m 38s master
master
45m 38s
chat : support Magistral thinking (#16413) CI (AMD) #30: Commit 128d522 pushed by ggerganov
1h 1m 26s master
master
1h 1m 26s
server : context checkpointing for hybrid and recurrent models (#16382) CI (AMD) #29: Commit f6dcda3 pushed by ggerganov
44m 1s master
master
44m 1s
metal : fix loop bound in ggml_mem_ranges (#16412) CI (AMD) #28: Commit 606a73f pushed by ggerganov
42m 16s master
master
42m 16s
llama : fix shapes for bert/mpt q/k norm (#16409) CI (AMD) #27: Commit 946f71e pushed by CISC
43m 39s master
master
43m 39s
ggml : fix graph reallocation with multiple chunks (#16396) CI (AMD) #26: Commit 638d330 pushed by slaren
45m 3s master
master
45m 3s
vulkan: Replace uses of maxMemoryAllocationSize and VK_WHOLE_SIZE (#1… CI (AMD) #25: Commit 2aaf0a2 pushed by 0cc4m
45m 51s master
master
45m 51s
vulkan: Fix FA coopmat1 invalid array indexing (#16365) CI (AMD) #24: Commit 0e1f838 pushed by 0cc4m
43m 39s master
master
43m 39s