Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
12,552 workflow run results
12,552 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA: fuse rope + set_rows CI #29554: Pull request #16884 opened by am17an
1h 15m 56s am17an:cuda-add-rope-fusion
am17an:cuda-add-rope-fusion
1h 15m 56s
vulkan: Fix crash when FP16 mul_mat accumulation is not supported CI #29553: Pull request #16796 synchronize by rillomas
30m 37s rillomas:fix-accf16-capability-crash
rillomas:fix-accf16-capability-crash
30m 37s
ggml-hexagon: respect input size when getting/setting tensor data (#1… CI #29552: Commit 13002a0 pushed by max-krasnyansky
1h 6m 15s master
master
1h 6m 15s
Disable NUMA-specific chunking for high-core-count HPC systems CI #29551: Pull request #16882 opened by rageshh-fj
3h 4m 21s rageshh-fj:rageshh-fj-llama-ggml-cpu-chunking
rageshh-fj:rageshh-fj-llama-ggml-cpu-chunking
3h 4m 21s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) CI #29550: Pull request #16574 synchronize by pockers21
52m 44s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
52m 44s
vulkan: fuse mul_mat+add and mul_mat_id+add_id CI #29549: Pull request #16868 synchronize by jeffbolznv
1h 16m 33s jeffbolznv:mmv_add_fusion
jeffbolznv:mmv_add_fusion
1h 16m 33s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) CI #29548: Pull request #16574 synchronize by pockers21
21m 0s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
21m 0s
ggml-hexagon: respect input size when getting/setting tensor data CI #29547: Pull request #16836 synchronize by l3utterfly
1h 40m 44s l3utterfly:patch-1
l3utterfly:patch-1
1h 40m 44s
server: add support for local image path loading for server CI #29546: Pull request #16874 synchronize by cchadowitz
Action required Pixel-Forensics-Inc:server-local-image-loading
Pixel-Forensics-Inc:server-local-image-loading
Action required
improve CUDA cpy memory bandwidth when copying transposed tensor CI #29545: Pull request #16841 synchronize by bssrdf
4h 1m 40s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
4h 1m 40s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) CI #29544: Pull request #16817 synchronize by GittyBurstein
3h 38m 25s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
3h 38m 25s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) CI #29543: Pull request #16817 synchronize by GittyBurstein
18s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
18s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) CI #29542: Pull request #16817 synchronize by GittyBurstein
17s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
17s
improve CUDA cpy memory bandwidth when copying transposed tensor CI #29541: Pull request #16841 synchronize by bssrdf
25m 38s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
25m 38s
vulkan: fuse mul_mat+add and mul_mat_id+add_id CI #29540: Pull request #16868 synchronize by jeffbolznv
3h 7m 54s jeffbolznv:mmv_add_fusion
jeffbolznv:mmv_add_fusion
3h 7m 54s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) CI #29539: Pull request #16817 synchronize by GittyBurstein
14m 10s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
14m 10s
mtmd: refactor preprocessing + support max/min pixels CI #29538: Pull request #16878 opened by ngxson
2h 39m 2s ngxson:xsn/mtmd-max-min-pixels
ngxson:xsn/mtmd-max-min-pixels
2h 39m 2s
rpc: use XXHash64 instead of FNV-1a for hashing tensors CI #29537: Pull request #16753 synchronize by jukofyork
2h 53m 23s jukofyork:rpc-xxhash
jukofyork:rpc-xxhash
2h 53m 23s
rpc: use XXHash64 instead of FNV-1a for hashing tensors CI #29536: Pull request #16753 synchronize by jukofyork
4m 9s jukofyork:rpc-xxhash
jukofyork:rpc-xxhash
4m 9s
Update llama-quant.cpp llama_tensor_get_type with DeepSeek friendly modifications CI #29535: Pull request #12727 synchronize by bartowski1182
3h 0m 3s bartowski1182:quant_types
bartowski1182:quant_types
3h 0m 3s
vulkan: fix shmem overrun in mmq id shader CI #29534: Pull request #16873 synchronize by ggerganov
5h 44m 9s 0cc4m/vulkan-workaround-mmqid-shmem-bug
0cc4m/vulkan-workaround-mmqid-shmem-bug
5h 44m 9s
Model: Minimax M2 CI #29533: Pull request #16831 reopened by pwilkin
4h 16m 24s pwilkin:minimax-m2
pwilkin:minimax-m2
4h 16m 24s
Model: Minimax M2 CI #29532: Pull request #16831 synchronize by pwilkin
10s pwilkin:minimax-m2
pwilkin:minimax-m2
10s
improve CUDA cpy memory bandwidth when copying transposed tensor CI #29531: Pull request #16841 synchronize by bssrdf
2h 59m 27s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
2h 59m 27s
improve CUDA cpy memory bandwidth when copying transposed tensor CI #29530: Pull request #16841 synchronize by bssrdf
1m 34s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
1m 34s