Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
11,641 workflow run results
11,641 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal: optimise GGML_OP_SUM CI #28756: Pull request #16559 opened by cern1710
47m 4s cern1710:metal-optimize-op-sum
cern1710:metal-optimize-op-sum
47m 4s
CANN: fix CPU memory leak in CANN backend (#16549) CI #28755: Commit 56fc38b pushed by hipudding
1h 12m 5s master
master
1h 12m 5s
metal: add support for opt_step_sgd (#16539) CI #28754: Commit 3f750f8 pushed by ggerganov
1h 28m 47s master
master
1h 28m 47s
ggml : fix scalar path for computing norm (#16558) CI #28753: Commit c515fc5 pushed by ggerganov
55m 10s master
master
55m 10s
metal: add support for opt_step_sgd CI #28751: Pull request #16539 synchronize by cern1710
1h 47m 22s cern1710:metal-opt-step-sgd
cern1710:metal-opt-step-sgd
1h 47m 22s
ggml : fix scalar path for computing norm CI #28750: Pull request #16558 opened by ggerganov
2h 46m 34s gg/ggml-fix-cpu-norm-scalar
gg/ggml-fix-cpu-norm-scalar
2h 46m 34s
Remove Legacy Copy-OP Pointer Indirection Code CI #28749: Pull request #16485 synchronize by anavp-nvidia
1h 58m 9s anavp-nvidia:remove_copy_op_pointer_indirection
anavp-nvidia:remove_copy_op_pointer_indirection
1h 58m 9s
CUDA: use fastdiv + ggml_cuda_mad for mmvf CI #28748: Pull request #16557 opened by am17an
45m 52s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
45m 52s
opencl: fix build targeting CL 2 CI #28747: Pull request #16554 opened by lhez
1h 38m 46s CodeLinaro:cl2-target-fix
CodeLinaro:cl2-target-fix
1h 38m 46s
CANN: fix CPU memory leak in CANN backend CI #28746: Pull request #16549 opened by noemotiovon
46m 7s noemotiovon:fix_mem_leak
noemotiovon:fix_mem_leak
46m 7s
Add experimental ggml-hexagon backend for the Hexagon NPU CI #28745: Pull request #16547 synchronize by max-krasnyansky
1h 2m 5s CodeLinaro:hexagon
CodeLinaro:hexagon
1h 2m 5s
Add experimental ggml-hexagon backend for the Hexagon NPU CI #28744: Pull request #16547 synchronize by max-krasnyansky
6m 22s CodeLinaro:hexagon
CodeLinaro:hexagon
6m 22s
Add experimental ggml-hexagon backend for the Hexagon NPU CI #28743: Pull request #16547 synchronize by max-krasnyansky
8m 57s CodeLinaro:hexagon
CodeLinaro:hexagon
8m 57s
Add experimental ggml-hexagon backend for the Hexagon NPU CI #28741: Pull request #16547 opened by max-krasnyansky
36m 37s CodeLinaro:hexagon
CodeLinaro:hexagon
36m 37s
CANN: Update several operators to support FP16 data format (#16251) CI #28740: Commit f9bc66c pushed by hipudding
42m 11s master
master
42m 11s
embedding: add raw option for --embd-output-format CI #28739: Pull request #16541 synchronize by SamMalayek
49m 34s SamMalayek:feature/raw-embedding-output
SamMalayek:feature/raw-embedding-output
49m 34s
CUDA: enable FA for FP32 KV cache CI #28738: Pull request #16546 opened by JohannesGaessler
1h 1m 51s JohannesGaessler:cuda-fa-f32
JohannesGaessler:cuda-fa-f32
1h 1m 51s
vulkan: Improve build time for MSVC CI #28737: Pull request #16545 opened by jeffbolznv
58m 53s jeffbolznv:CMP0147
jeffbolznv:CMP0147
58m 53s
tests: increase NMSE threshold for q5_1 MUL_MAT tests CI #28734: Pull request #16544 opened by Erics38
1h 11m 58s Erics38:fix/q5_1-test-threshold
Erics38:fix/q5_1-test-threshold
1h 11m 58s
vulkan: Support FA with K/V in F32 CI #28733: Pull request #16543 opened by jeffbolznv
1h 5m 29s jeffbolznv:FA_f32
jeffbolznv:FA_f32
1h 5m 29s
CUDA: fix numerical issue in tile FA kernel CI #28730: Pull request #16540 synchronize by JohannesGaessler
1h 17m 37s JohannesGaessler:cuda-fa-fix-numerics
JohannesGaessler:cuda-fa-fix-numerics
1h 17m 37s
graph : support cacheless embeddings with FA and iSWA CI #28729: Pull request #16528 synchronize by JohannesGaessler
1h 2m 21s gg/cacheless-embd
gg/cacheless-embd
1h 2m 21s
CUDA: fix numerical issue in tile FA kernel CI #28728: Pull request #16540 opened by JohannesGaessler
11m 13s JohannesGaessler:cuda-fa-fix-numerics
JohannesGaessler:cuda-fa-fix-numerics
11m 13s
metal: add support for opt_step_sgd CI #28727: Pull request #16539 opened by cern1710
52m 42s cern1710:metal-opt-step-sgd
cern1710:metal-opt-step-sgd
52m 42s
metal : add opt_step_adamw and op_sum (#16529) CI #28726: Commit a31cf36 pushed by ggerganov
44m 29s master
master
44m 29s