Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
12,045 workflow run results
12,045 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add LFM2 tool handling CI #29220: Pull request #16763 synchronize by ykhrustalev
1h 11m 13s ykhrustalev:ykhrustalev/lfm2-func-calling
ykhrustalev:ykhrustalev/lfm2-func-calling
1h 11m 13s
model : add LightOnOCR-1B model CI #29219: Pull request #16764 opened by ngxson
55m 48s ngxson:xsn/lighton-ocr
ngxson:xsn/lighton-ocr
55m 48s
Add LFM2 tool handling CI #29218: Pull request #16763 opened by ykhrustalev
36m 58s ykhrustalev:ykhrustalev/lfm2-func-calling
ykhrustalev:ykhrustalev/lfm2-func-calling
36m 58s
Refactor llama-model.cpp CI #29217: Pull request #16252 synchronize by pwilkin
47m 42s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
47m 42s
Refactor llama-model.cpp CI #29216: Pull request #16252 synchronize by pwilkin
17m 40s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
17m 40s
ggml: fix CUDA grid launch condition for large block_nums.y in binbca… CI #29215: Commit 55945d2 pushed by JohannesGaessler
48m 24s master
master
48m 24s
ggml: fix CUDA grid launch condition for large block_nums.y in binbcast CI #29214: Pull request #16742 synchronize by leejet
1h 4m 40s leejet:cuda_bincast_fix
leejet:cuda_bincast_fix
1h 4m 40s
ggml: fix cuda kernel launch configuration for k_compute_batched_ptrs to support large batch CI #29213: Pull request #16744 synchronize by leejet
1h 18m 18s leejet:cuda_mul_mat_fix
leejet:cuda_mul_mat_fix
1h 18m 18s
ggml: fix cuda kernel launch configuration for k_compute_batched_ptrs to support large batch CI #29212: Pull request #16744 synchronize by leejet
2m 58s leejet:cuda_mul_mat_fix
leejet:cuda_mul_mat_fix
2m 58s
Refactor llama-model.cpp CI #29211: Pull request #16252 synchronize by pwilkin
59m 21s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
59m 21s
Refactor llama-model.cpp CI #29210: Pull request #16252 synchronize by pwilkin
5m 53s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
5m 53s
Refactor llama-model.cpp CI #29209: Pull request #16252 synchronize by pwilkin
5m 17s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
5m 17s
llama-cli: add support for reasoning CI #29208: Pull request #16603 synchronize by bandoti
1h 10m 19s bandoti:llamacli-reasoning2
bandoti:llamacli-reasoning2
1h 10m 19s
CUDA: use CUB for arbitary size argsort (#16754) CI #29207: Commit 0bcb40b pushed by am17an
56m 16s master
master
56m 16s
qwen3-coder tool call parser CI #29206: Pull request #16755 synchronize by marceldev89
Action required marceldev89:qwen3-coder_tool_call_parser
marceldev89:qwen3-coder_tool_call_parser
Action required
llama: consistent ctx <-> buf order for KV cache CI #29205: Pull request #16746 synchronize by JohannesGaessler
57m 50s JohannesGaessler:llama-kv-cache-fix-ctx-order
JohannesGaessler:llama-kv-cache-fix-ctx-order
57m 50s
metal : initial Metal4 tensor API support CI #29204: Pull request #16634 synchronize by ggerganov
1h 5m 5s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
1h 5m 5s
CUDA: use CUB for arbitary size argsort CI #29203: Pull request #16754 opened by am17an
59m 44s am17an:cuda_cub_argsort
am17an:cuda_cub_argsort
59m 44s
rpc: use XXHash64 instead of FNV-1a for hashing tensors CI #29202: Pull request #16753 opened by jukofyork
59m 44s jukofyork:rpc-xxhash
jukofyork:rpc-xxhash
59m 44s
cann: improve device ID handling and aclnnArange checks CI #29201: Pull request #16752 synchronize by noemotiovon
51m 39s noemotiovon:compatibility
noemotiovon:compatibility
51m 39s
cann: improve device ID handling and aclnnArange checks CI #29200: Pull request #16752 synchronize by noemotiovon
4m 34s noemotiovon:compatibility
noemotiovon:compatibility
4m 34s
cann: improve device ID handling and aclnnArange checks CI #29199: Pull request #16752 opened by noemotiovon
51m 3s noemotiovon:compatibility
noemotiovon:compatibility
51m 3s
CUDA: General GEMV fusion CI #29198: Pull request #16715 synchronize by am17an
50m 39s am17an:cuda_fuse_gate_bias
am17an:cuda_fuse_gate_bias
50m 39s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) CI #29197: Pull request #16574 synchronize by pockers21
56m 33s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
56m 33s
llama : disable pipeline parallelism if compute buffer allocation fails CI #29195: Pull request #16748 opened by slaren
58m 40s sl/auto-disable-pipeline-parallelism
sl/auto-disable-pipeline-parallelism
58m 40s