Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
6,867 workflow run results
6,867 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

kv-cache : refactor + add llama_memory_state_i CI #23066: Pull request #13746 synchronize by ggerganov
53m 49s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
53m 49s
kv-cache : refactor + add llama_memory_state_i CI #23065: Pull request #13746 synchronize by ggerganov
52s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
52s
kv-cache : refactor + add llama_memory_state_i CI #23064: Pull request #13746 synchronize by ggerganov
3m 0s gg/kv-cache-simplify-part3
gg/kv-cache-simplify-part3
3m 0s
tests : add test-tokenizers-remote CI #23063: Pull request #13846 synchronize by CISC
55m 32s cisc/test-tokenizers-remote
cisc/test-tokenizers-remote
55m 32s
server: fix remove 'image_url'/'input_audio' json-object effectlly for 'llama_params' in multimodal-model-mode CI #23062: Pull request #13853 opened by flyinskyin2013
54m 41s flyinskyin2013:master
flyinskyin2013:master
54m 41s
CUDA: fix FA tg at long context for CC >= 8.9 CI #23061: Pull request #13852 opened by JohannesGaessler
49m 33s JohannesGaessler:cuda-fix-fa-long-context
JohannesGaessler:cuda-fix-fa-long-context
49m 33s
musa: enable fp16 mma (all) and cublas on qy2 CI #23060: Pull request #13842 synchronize by yeahdongcn
1h 24m 19s makllama:xd/mma_blas
makllama:xd/mma_blas
1h 24m 19s
tests : add test-tokenizers-remote CI #23059: Pull request #13846 synchronize by CISC
1h 21m 33s cisc/test-tokenizers-remote
cisc/test-tokenizers-remote
1h 21m 33s
musa: enable fp16 mma (all) and cublas on qy2 CI #23058: Pull request #13842 synchronize by yeahdongcn
18m 36s makllama:xd/mma_blas
makllama:xd/mma_blas
18m 36s
tests : add test-tokenizers-remote CI #23056: Pull request #13846 synchronize by CISC
54m 51s cisc/test-tokenizers-remote
cisc/test-tokenizers-remote
54m 51s
tests : add test-tokenizers-remote CI #23055: Pull request #13846 opened by CISC
5m 43s cisc/test-tokenizers-remote
cisc/test-tokenizers-remote
5m 43s
llama : auto-batch preparation CI #23054: Pull request #13845 opened by ggerganov
1h 5m 23s gg/auto-batch
gg/auto-batch
1h 5m 23s
llama : use n_swa + n_ubatch cells for SWA cache CI #23053: Pull request #13833 synchronize by ggerganov
52m 7s gg/swa-optimize
gg/swa-optimize
52m 7s
ggml: aarch64: Implement SVE F32 kernels for vector functions CI #23052: Pull request #13843 opened by vineelabhinav
52m 26s vineelabhinav:F32-vec-SVE
vineelabhinav:F32-vec-SVE
52m 26s
musa: enable fp16 mma (all) and cublas on qy2 CI #23051: Pull request #13842 opened by yeahdongcn
52m 32s makllama:xd/mma_blas
makllama:xd/mma_blas
52m 32s
SYCL: Implement few same quantized type copy kernels CI #23050: Pull request #13739 synchronize by qnixsynapse
51m 32s sycl/same_q_cpy
sycl/same_q_cpy
51m 32s
kv-cache : avoid modifying recurrent cells when setting inputs CI #23048: Pull request #13834 synchronize by compilade
1h 19m 52s compilade/readonly-recurrent-inputs
compilade/readonly-recurrent-inputs
1h 19m 52s
CANN: Add SOC TYPE printing in cmake configuration (#13837) CI #23047: Commit 1e8659e pushed by hipudding
1h 2m 12s master
master
1h 2m 12s
[CANN]: Add SOC TYPE printing in cmake configuration processing CI #23046: Pull request #13837 opened by leo-pony
1h 0m 4s leo-pony:master
leo-pony:master
1h 0m 4s
feat: Hybrid unified/recurrent cache CI #23044: Pull request #13276 synchronize by gabe-l-hart
54m 24s gabe-l-hart:HybridCache
gabe-l-hart:HybridCache
54m 24s
opencl: add new ops - argsort, div, sub, addrows, sigmoid, … CI #23041: Commit a3c3084 pushed by max-krasnyansky
1h 13m 54s master
master
1h 13m 54s
opencl: mark mul_mat f32f32 as supporting non-contiguous tensors … CI #23040: Commit 1701d4c pushed by max-krasnyansky
47m 33s master
master
47m 33s
kv-cache : avoid modifying recurrent cells when setting inputs CI #23039: Pull request #13834 opened by compilade
1h 26m 12s compilade/readonly-recurrent-inputs
compilade/readonly-recurrent-inputs
1h 26m 12s
llama : use n_swa + n_ubatch cells for SWA cache CI #23038: Pull request #13833 opened by ggerganov
2h 3m 55s gg/swa-optimize
gg/swa-optimize
2h 3m 55s
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) CI #23037: Commit bef8176 pushed by 0cc4m
2h 29m 46s master
master
2h 29m 46s