Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
10,413 workflow run results
10,413 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml: allow casting between f32 and i32 CI #27015: Pull request #15783 synchronize by ngxson
1h 5m 36s ngxson:xsn/ggml_cast_f32_i32
ngxson:xsn/ggml_cast_f32_i32
1h 5m 36s
opencl: initial q8_0 mv support CI #27014: Pull request #15732 synchronize by lhez
1h 25m 42s CodeLinaro:q8_0-mv
CodeLinaro:q8_0-mv
1h 25m 42s
CANN: Refactor ND to NZ workspace to be per-device in Ascend backend CI #27013: Pull request #15763 synchronize by noemotiovon
1h 4m 55s noemotiovon:fix_nz
noemotiovon:fix_nz
1h 4m 55s
CANN: Fix precision issue on 310I DUO multi-devices CI #27012: Pull request #15784 opened by hipudding
34m 31s hipudding:310_multidev
hipudding:310_multidev
34m 31s
CANN: fix acl_rstd allocation size in ggml_cann_rms_norm (#15760) CI #27011: Commit 239b60e pushed by hipudding
1h 34m 7s master
master
1h 34m 7s
CANN: Refactor ND to NZ workspace to be per-device in Ascend backend CI #27010: Pull request #15763 synchronize by noemotiovon
1h 33m 21s noemotiovon:fix_nz
noemotiovon:fix_nz
1h 33m 21s
CUDA: Add mul_mat_id support for the mmf kernel CI #27009: Pull request #15767 synchronize by am17an
1h 47m 10s am17an:mul_mat_id_for_mmf
am17an:mul_mat_id_for_mmf
1h 47m 10s
CANN: Refactor ND to NZ workspace to be per-device in Ascend backend CI #27008: Pull request #15763 synchronize by noemotiovon
5m 49s noemotiovon:fix_nz
noemotiovon:fix_nz
5m 49s
ggml: allow casting between f32 and i32 CI #27007: Pull request #15783 opened by ngxson
1h 13m 15s ngxson:xsn/ggml_cast_f32_i32
ngxson:xsn/ggml_cast_f32_i32
1h 13m 15s
server: add exceed_context_size_error type CI #27005: Pull request #15780 synchronize by ngxson
1h 3m 0s ngxson:xsn/exceed_context_size_error
ngxson:xsn/exceed_context_size_error
1h 3m 0s
server: add exceed_context_size_error type CI #27004: Pull request #15780 opened by ngxson
8m 31s ngxson:xsn/exceed_context_size_error
ngxson:xsn/exceed_context_size_error
8m 31s
vulkan: fix mmv subgroup16 selection (#15775) CI #26997: Commit dff7551 pushed by ericcurtin
1h 13m 58s master
master
1h 13m 58s
vulkan: don't use std::string in load_shaders, to improve compile tim… CI #26996: Commit 0fce7a1 pushed by 0cc4m
2h 11m 34s master
master
2h 11m 34s
vulkan : update ggml_vk_instance_validation_ext_available (#15666) CI #26995: Commit 8227695 pushed by 0cc4m
2h 1m 2s master
master
2h 1m 2s
ggml vulkan: add hardsigmoid and hardswish operations (#15762) CI #26994: Commit 0014fb4 pushed by 0cc4m
1h 38m 18s master
master
1h 38m 18s
Deepseek V3.1 native tool calling support (OpenAI Style) CI #26993: Pull request #15533 synchronize by createthis
1h 7m 43s createthis:deepseek_3_1_thinking_mode
createthis:deepseek_3_1_thinking_mode
1h 7m 43s
vulkan: fix mmv subgroup16 selection CI #26992: Pull request #15775 opened by 0cc4m
1h 36m 37s 0cc4m/vulkan-fix-mmv-subgroup16-selection
0cc4m/vulkan-fix-mmv-subgroup16-selection
1h 36m 37s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1… CI #26991: Commit 661ae31 pushed by JohannesGaessler
1h 9m 14s master
master
1h 9m 14s
Document the new max GPU layers default in help CI #26989: Pull request #15771 synchronize by ericcurtin
2h 11m 50s document-new-ngl-default
document-new-ngl-default
2h 11m 50s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26988: Pull request #15715 synchronize by ORippler
2h 6m 45s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
2h 6m 45s
Document the new max GPU layers default in help CI #26987: Pull request #15771 synchronize by ericcurtin
16m 12s document-new-ngl-default
document-new-ngl-default
16m 12s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26986: Pull request #15715 synchronize by ORippler
13m 18s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
13m 18s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26985: Pull request #15715 synchronize by ORippler
17m 1s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
17m 1s
sampling : optimize dist sampler (#15704) CI #26984: Commit cdedb70 pushed by ggerganov
2h 11m 19s master
master
2h 11m 19s
Document the new max GPU layers default in help CI #26983: Pull request #15771 opened by ericcurtin
24m 22s document-new-ngl-default
document-new-ngl-default
24m 22s