Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
10,229 workflow run results
10,229 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

OpenCL: add hs=40 support to FA CI #26941: Pull request #15758 opened by rmatif
1h 12m 56s rmatif:add-h40-fa
rmatif:add-h40-fa
1h 12m 56s
gguf: gguf_writer refactor CI #26940: Pull request #15691 synchronize by Green-Sky
3h 26m 2s Green-Sky:gguf_write_refactor
Green-Sky:gguf_write_refactor
3h 26m 2s
convert : use reflinks for faster conversion CI #26939: Pull request #15727 synchronize by compilade
1h 12m 47s compilade/convert-reflinks
compilade/convert-reflinks
1h 12m 47s
fix: resolve unsigned int initialization warning for n_dims/size in g… CI #26938: Commit 3de0082 pushed by JohannesGaessler
1h 12m 22s master
master
1h 12m 22s
convert : use reflinks for faster conversion CI #26937: Pull request #15727 synchronize by compilade
2m 49s compilade/convert-reflinks
compilade/convert-reflinks
2m 49s
ggml-cpu: fixes instability in NNPA Vector Intrinsics CI #26932: Pull request #15739 synchronize by taronaeo
1m 55s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
1m 55s
ggml-cpu: fixes instability in NNPA Vector Intrinsics CI #26931: Pull request #15739 synchronize by taronaeo
7m 20s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
7m 20s
ggml-cpu: fixes instability in NNPA Vector Intrinsics CI #26930: Pull request #15739 synchronize by taronaeo
1m 27s taronaeo:fix/14877-instable-nnpa
taronaeo:fix/14877-instable-nnpa
1m 27s
fix: resolve unsigned integer initialization warnings in gguf.cpp CI #26929: Pull request #15754 opened by skrandy
1h 2m 11s skrandy:fix-uint-warning
skrandy:fix-uint-warning
1h 2m 11s
ggml: add ops for WAN video model (cuda && cpu) CI #26928: Pull request #15669 synchronize by leejet
1h 18m 6s leejet:wan
leejet:wan
1h 18m 6s
ggml: add ops for WAN video model (cuda && cpu) CI #26927: Pull request #15669 synchronize by leejet
35m 22s leejet:wan
leejet:wan
35m 22s
llama: -fa 1/0/-1 aliases for -fa on/off/auto (#15746) CI #26926: Commit c466abe pushed by JohannesGaessler
1h 24m 57s master
master
1h 24m 57s
ggml: add ops for WAN video model (cuda && cpu) CI #26925: Pull request #15669 synchronize by leejet
6m 0s leejet:wan
leejet:wan
6m 0s
ggml: add ops for WAN video model (cuda && cpu) CI #26924: Pull request #15669 synchronize by leejet
2m 11s leejet:wan
leejet:wan
2m 11s
Consolidate multiple tensor copies to reduce API overhead CI #26923: Pull request #15750 opened by agray3
1h 8m 59s agray3:ag_bulk_copy_tensor
agray3:ag_bulk_copy_tensor
1h 8m 59s
gguf: gguf_writer refactor CI #26922: Pull request #15691 synchronize by Green-Sky
4h 20m 58s Green-Sky:gguf_write_refactor
Green-Sky:gguf_write_refactor
4h 20m 58s
llama: -fa 1/0/-1 aliases for -fa on/off/auto CI #26921: Pull request #15746 synchronize by JohannesGaessler
1h 7m 21s JohannesGaessler:llama-fa-alias
JohannesGaessler:llama-fa-alias
1h 7m 21s
llama: -fa 1/0/-1 aliases for -fa on/off/auto CI #26920: Pull request #15746 opened by JohannesGaessler
7m 29s JohannesGaessler:llama-fa-alias
JohannesGaessler:llama-fa-alias
7m 29s
tests : add --list-ops and --show-coverage options CI #26919: Pull request #15745 opened by danbev
1h 20m 59s danbev:test-backend-ops-list-tests
danbev:test-backend-ops-list-tests
1h 20m 59s
vulkan: fix shaders gen when no integer dot is available (#15740) CI #26918: Commit 0a2a384 pushed by 0cc4m
1h 34m 15s master
master
1h 34m 15s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26917: Pull request #15715 synchronize by ORippler
1h 30m 32s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
1h 30m 32s
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E CI #26916: Pull request #15715 synchronize by ORippler
3m 27s ORippler:osimons/optimize_fused_rms_norm_f32
ORippler:osimons/optimize_fused_rms_norm_f32
3m 27s
ggml: add ops for WAN video model (cuda && cpu) CI #26915: Pull request #15669 synchronize by leejet
1h 12m 44s leejet:wan
leejet:wan
1h 12m 44s
vulkan: don't use std::string in load_shaders, to improve compile time CI #26914: Pull request #15724 synchronize by jeffbolznv
1h 33m 0s jeffbolznv:load_shaders_const_char
jeffbolznv:load_shaders_const_char
1h 33m 0s
ggml: add ops for WAN video model (cuda && cpu) CI #26913: Pull request #15669 synchronize by leejet
38m 58s leejet:wan
leejet:wan
38m 58s