Skip to content

Actions: ngxson/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
1,532 workflow run results
1,532 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : add support for embd_normalize parameter (#14964) CI #1824: Commit 41e78c5 pushed by ngxson
1h 15m 5s master
master
1h 15m 5s
HIP: enable mfma mmq on gfx908 and gfx90a for select datatypes and sh… CI #1823: Commit ad4a700 pushed by ngxson
1h 0m 39s master
master
1h 0m 39s
sync : ggml CI #1822: Commit e32a4ec pushed by ngxson
59m 21s master
master
59m 21s
CUDA: skip masked KV slices for all FA kernels (#14924) CI #1821: Commit 92b8810 pushed by ngxson
1h 10m 39s master
master
1h 10m 39s
tests : update for LLAMA_SET_ROWS=1 (#14961) CI #1820: Commit 00131d6 pushed by ngxson
1h 5m 48s master
master
1h 5m 48s
graph : fix stack-use-after-return (#14960) CI #1819: Commit 1e15bfd pushed by ngxson
1h 8m 50s master
master
1h 8m 50s
embeddings: fix extraction of CLS pooling results (#14927) CI #1818: Commit a118d80 pushed by ngxson
1h 3m 36s master
master
1h 3m 36s
HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only … CI #1817: Commit aa79524 pushed by ngxson
57m 39s master
master
57m 39s
HIP: add GGML_HIP_MMQ_MFMA option to allow disableing the MFMA path. … CI #1816: Commit b77d111 pushed by ngxson
1h 10m 14s master
master
1h 10m 14s
common : avoid logging partial messages (which can contain broken UTF… CI #1815: Commit 1a67fcc pushed by ngxson
1h 9m 56s master
master
1h 9m 56s
CANN: Add ggml_set_rows (#14943) CI #1814: Commit 204f2cf pushed by ngxson
58m 25s master
master
58m 25s
cuda : add softcap fusion (#14907) CI #1813: Commit 138b288 pushed by ngxson
1h 2m 11s master
master
1h 2m 11s
CUDA: add roll (#14919) CI #1812: Commit 0a5036b pushed by ngxson
58m 33s master
master
58m 33s
test-backend-ops : extend test case filtering (#14865) CI #1811: Commit bda6219 pushed by ngxson
1h 11m 37s master
master
1h 11m 37s
llama-bench : use local GPUs along with RPC servers (#14917) CI #1810: Commit c556418 pushed by ngxson
1h 12m 27s master
master
1h 12m 27s
ggml-cpu : deduplicate scalar implementations (#14897) CI #1809: Commit db16e28 pushed by ngxson
1h 3m 25s master
master
1h 3m 25s
SYCL: Add set_rows support for quantized types (#14883) CI #1808: Commit cd1fce6 pushed by ngxson
55m 51s master
master
55m 51s
mtmd : add support for Voxtral (#14862) CI #1807: Commit 00fa15f pushed by ngxson
54m 16s master
master
54m 16s
CUDA: fix pointer incrementation in FA (#14916) CI #1806: Commit 946b1f6 pushed by ngxson
1h 7m 14s master
master
1h 7m 14s
model : add support for SmallThinker series (#14898) CI #1805: Commit 6c6e397 pushed by ngxson
59m 29s master
master
59m 29s
sycl: refactor quantization to q8_1 (#14815) CI #1804: Commit afc0e89 pushed by ngxson
1h 7m 27s master
master
1h 7m 27s
vulkan : add fp16 support for the conv_2d kernel (#14872) CI #1803: Commit 89d1029 pushed by ngxson
1h 3m 32s master
master
1h 3m 32s
vulkan: skip empty set_rows to avoid invalid API usage (#14860) CI #1802: Commit f1a4e72 pushed by ngxson
57m 47s master
master
57m 47s
model : make rope_yarn_log_mul optional for deepseek2 (#14896) CI #1801: Commit 4762ad7 pushed by ngxson
56m 1s master
master
56m 1s
llama : fix kq_scale for the attention layers of PLaMo2 (#14892) CI #1800: Commit 1dc9614 pushed by ngxson
54m 50s master
master
54m 50s