Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
5,411 workflow run results
5,411 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama-bench : Add --override-tensors arg CI #21511: Pull request #12922 synchronize by 4onen
41m 18s 4onen:llama-bench-tensor-override
4onen:llama-bench-tensor-override
41m 18s
opencl: split ggml-opencl.cl into multiple files and cleanup (#12886) CI #21510: Commit 80f19b4 pushed by max-krasnyansky
5m 27s master
master
5m 27s
server : use std::move whenever possible CI #21509: Pull request #12936 synchronize by ngxson
42m 46s ngxson:xsn/server_std_move
ngxson:xsn/server_std_move
42m 46s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #21508: Pull request #12326 synchronize by jeffzhou2000
40m 42s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
40m 42s
kv-cache : separate recurrent vs non-recurrent impl CI #21507: Pull request #12799 synchronize by ggerganov
48m 19s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
48m 19s
kv-cache : separate recurrent vs non-recurrent impl CI #21506: Pull request #12799 synchronize by ggerganov
10m 8s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
10m 8s
[CANN]310P OPT Support CI #21505: Pull request #12962 opened by noemotiovon
1h 1m 58s noemotiovon:opt_support
noemotiovon:opt_support
1h 1m 58s
DeepSeek V2/V3 MLA optimisations (please ignore) CI #21504: Pull request #12961 opened by jukofyork
1h 48m 2s master-mla-optimise-q
master-mla-optimise-q
1h 48m 2s
kv-cache : separate recurrent vs non-recurrent impl CI #21503: Pull request #12799 synchronize by ggerganov
1h 25m 50s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
1h 25m 50s
Vulkan: Fix Deepseek V2 inference by making ggml_vk_op_supports_incontiguous(GGML_OP_RMS_NORM) return true CI #21502: Pull request #12960 opened by stduhpf
1h 27m 12s stduhpf:ds-fix
stduhpf:ds-fix
1h 27m 12s
metal : add memory pool for temp allocs CI #21501: Pull request #12850 synchronize by ggerganov
1h 33m 3s gg/metal-heap
gg/metal-heap
1h 33m 3s
metal : add FA-vec kernels for head size 96 (#12952) CI #21500: Commit f8f820c pushed by ggerganov
1h 11m 54s master
master
1h 11m 54s
CANN: Add x86 build ci (#12950) CI #21499: Commit 54a7272 pushed by ericcurtin
59m 39s master
master
59m 39s
CANN: Add support for async operator submission CI #21498: Pull request #12864 synchronize by hipudding
43m 13s hipudding:aync_submit
hipudding:aync_submit
43m 13s
CANN: Add support for async operator submission CI #21497: Pull request #12864 synchronize by hipudding
6m 28s hipudding:aync_submit
hipudding:aync_submit
6m 28s
Resolved half rope,multi-EOS issues in convert_hf_togguf.py for GLM4Z Model CI #21496: Pull request #12957 opened by piDack
45m 31s piDack:update_glm4z
piDack:update_glm4z
45m 31s
CUDA/HIP: Share the same unified memory allocation logic. (#12934) CI #21495: Commit 84778e9 pushed by IMbackK
56m 35s master
master
56m 35s
rpc : add RPC_CMD_HELLO CI #21494: Pull request #12955 opened by rgerganov
55m 20s rgerganov:rpc-hello
rgerganov:rpc-hello
55m 20s
SYCL: Add ROPE vision kernel (#12887) CI #21493: Commit 5106764 pushed by Rbiessy
1h 13m 54s master
master
1h 13m 54s
imatrix: add option to display importance score statistics for a given imatrix file CI #21492: Pull request #12718 synchronize by EAddario
1h 37m 9s EAddario:imatrix
EAddario:imatrix
1h 37m 9s
server : use std::move whenever possible CI #21491: Pull request #12936 synchronize by ngxson
1h 21m 26s ngxson:xsn/server_std_move
ngxson:xsn/server_std_move
1h 21m 26s
graph : make FA compatible with MLA + add initial Metal kernels CI #21490: Pull request #12953 opened by ggerganov
1h 13m 45s gg/mla
gg/mla
1h 13m 45s
server : use std::move whenever possible CI #21489: Pull request #12936 synchronize by ngxson
18m 1s ngxson:xsn/server_std_move
ngxson:xsn/server_std_move
18m 1s
llama : DeepSeek V2/V3 MLA implementation (#12801) CI #21488: Commit daa4228 pushed by ggerganov
1h 21m 26s master
master
1h 21m 26s
ggml : Add AVX512 implementation of GEMM - Q4_Kx8 (#12829) CI #21487: Commit eccc7a1 pushed by ggerganov
1h 33m 34s master
master
1h 33m 34s