Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
5,780 workflow run results
5,780 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[CANN] Optimize CANN buffer pool memory management CI #21458: Pull request #12875 synchronize by bachelor-dou
19m 29s bachelor-dou:test
bachelor-dou:test
19m 29s
Llama-3_1-Nemotron-Ultra-253B-v1 support CI #21457: Pull request #12843 synchronize by ymcki
47m 31s ymcki:master
ymcki:master
47m 31s
rpc : use ggml_context_ptr (#12938) CI #21456: Commit c772d54 pushed by rgerganov
53m 18s master
master
53m 18s
SYCL: Fix im2col CI #21455: Pull request #12910 synchronize by qnixsynapse
56m 21s fix_im2col
fix_im2col
56m 21s
[CANN]Opt ROPE optimization CI #21454: Pull request #12865 synchronize by noemotiovon
48m 31s noemotiovon:opt_support
noemotiovon:opt_support
48m 31s
[CANN]Opt ROPE optimization CI #21452: Pull request #12865 synchronize by noemotiovon
53m 37s noemotiovon:opt_support
noemotiovon:opt_support
53m 37s
rpc : use ggml_context_ptr CI #21451: Pull request #12938 opened by rgerganov
12m 41s rgerganov:rpc-ctx-ptr
rgerganov:rpc-ctx-ptr
12m 41s
metal : add memory pool for temp allocs CI #21450: Pull request #12850 synchronize by ggerganov
1h 11m 58s gg/metal-heap
gg/metal-heap
1h 11m 58s
[CANN]Opt ROPE optimization CI #21449: Pull request #12865 synchronize by noemotiovon
1h 19m 24s noemotiovon:opt_support
noemotiovon:opt_support
1h 19m 24s
server : use std::move whenever possible CI #21447: Pull request #12936 opened by ngxson
1h 25m 11s ngxson:xsn/server_std_move
ngxson:xsn/server_std_move
1h 25m 11s
server : vision support via libmtmd CI #21446: Pull request #12898 synchronize by ngxson
1h 26m 5s ngxson:xsn/server_mtmd
ngxson:xsn/server_mtmd
1h 26m 5s
sync : ggml CI #21445: Commit 526739b pushed by ggerganov
49m 51s master
master
49m 51s
sync : ggml CI #21444: Pull request #12935 opened by ggerganov
58m 5s sync-ggml-25-04-14
sync-ggml-25-04-14
58m 5s
ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into… CI #21443: Commit e959d32 pushed by ggerganov
1h 9m 18s master
master
1h 9m 18s
CUDA/HIP: Share the same unified memory allocation logic. CI #21442: Pull request #12934 opened by hjc4869
46m 53s hjc4869:hip-uma
hjc4869:hip-uma
46m 53s
imatrix: add option to display importance score statistics for a given imatrix file CI #21441: Pull request #12718 synchronize by EAddario
59m 5s EAddario:imatrix
EAddario:imatrix
59m 5s
mtmd : add methods to access mtmd_image_tokens CI #21440: Pull request #12906 synchronize by ngxson
55m 13s ngxson:xsn/mtmd_image_api
ngxson:xsn/mtmd_image_api
55m 13s
server : vision support via libmtmd CI #21439: Pull request #12898 synchronize by ngxson
55m 52s ngxson:xsn/server_mtmd
ngxson:xsn/server_mtmd
55m 52s
ggml: disable CUDA graphs for unsupported DUP and CONT node types (#1… CI #21438: Commit 307bfa2 pushed by slaren
46m 19s master
master
46m 19s
quantize: Handle user-defined quantization levels for additional tens… CI #21437: Commit 71e90e8 pushed by ggerganov
54m 5s master
master
54m 5s
vulkan: enable coopmat2 FA gqa and split_k optimizations more often CI #21436: Pull request #12931 opened by jeffbolznv
45m 33s jeffbolznv:fa_better_scaling
jeffbolznv:fa_better_scaling
45m 33s
llava: add performance print for gemma3 example CI #21435: Pull request #12929 opened by Russyyds
55m 51s Russyyds:add_gemma3_perf_print
Russyyds:add_gemma3_perf_print
55m 51s
Add Qwen2.5VL support CI #21434: Pull request #12402 synchronize by HimariO
40m 29s HimariO:qwen25-vl
HimariO:qwen25-vl
40m 29s
DeepSeek V2/V3 MLA implementation CI #21433: Pull request #12801 synchronize by jukofyork
46m 6s mla--ready-for-review
mla--ready-for-review
46m 6s
DeepSeek V2/V3 MLA implementation CI #21432: Pull request #12801 synchronize by jukofyork
5m 25s mla--ready-for-review
mla--ready-for-review
5m 25s