Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
1,049 workflow run results
1,049 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CANN: Add support for async operator submission (#12864) Server #1341: Commit 7a395f6 pushed by ngxson
9m 19s master
master
9m 19s
llama : recognize IBM Granite 3.3 FIM tokens (#12988) Server #1340: Commit 971f245 pushed by ngxson
11m 55s master
master
11m 55s
opencl: fix incorrect local_size index in profiling log (#12868) Server #1339: Commit 12b1750 pushed by ngxson
8m 43s master
master
8m 43s
vulkan: enable coopmat2 FA gqa and split_k optimizations more often (… Server #1338: Commit 015022b pushed by ngxson
8m 59s master
master
8m 59s
CANN: Add 310P operator support check (#12962) Server #1337: Commit b43d89e pushed by ngxson
10m 52s master
master
10m 52s
opencl: split ggml-opencl.cl into multiple files and cleanup (#12886) Server #1336: Commit 80f19b4 pushed by ngxson
8m 25s master
master
8m 25s
metal : add FA-vec kernels for head size 96 (#12952) Server #1335: Commit f8f820c pushed by ngxson
8m 36s master
master
8m 36s
CANN: Add x86 build ci (#12950) Server #1334: Commit 54a7272 pushed by ngxson
8m 24s master
master
8m 24s
CUDA/HIP: Share the same unified memory allocation logic. (#12934) Server #1333: Commit 84778e9 pushed by ngxson
6m 38s master
master
6m 38s
SYCL: Add ROPE vision kernel (#12887) Server #1332: Commit 5106764 pushed by ngxson
9m 36s master
master
9m 36s
llama : DeepSeek V2/V3 MLA implementation (#12801) Server #1331: Commit daa4228 pushed by ngxson
9m 26s master
master
9m 26s
ggml : Add AVX512 implementation of GEMM - Q4_Kx8 (#12829) Server #1330: Commit eccc7a1 pushed by ngxson
9m 38s master
master
9m 38s
CANN: Opt ROPE optimization (#12865) Server #1329: Commit 0019279 pushed by ngxson
10m 4s master
master
10m 4s
CANN: Optimize CANN buffer pool memory management (#12875) Server #1328: Commit b0c75ac pushed by ngxson
8m 33s master
master
8m 33s
Add performance print for gemma3 in example (#12929) Server #1327: Commit d6d2c2a pushed by ngxson
9m 26s master
master
9m 26s
SYCL: Fix im2col (#12910) Server #1326: Commit 75afa0a pushed by ngxson
8m 49s master
master
8m 49s
rpc : use ggml_context_ptr (#12938) Server #1325: Commit c772d54 pushed by ngxson
11m 34s master
master
11m 34s
sync : ggml Server #1324: Commit 526739b pushed by ngxson
8m 44s master
master
8m 44s
ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into… Server #1323: Commit e959d32 pushed by ngxson
10m 5s master
master
10m 5s
ggml: disable CUDA graphs for unsupported DUP and CONT node types (#1… Server #1322: Commit 307bfa2 pushed by ngxson
8m 20s master
master
8m 20s
quantize: Handle user-defined quantization levels for additional tens… Server #1321: Commit 71e90e8 pushed by ngxson
8m 16s master
master
8m 16s
common : Define cache directory on AIX (#12915) Server #1320: Commit bc091a4 pushed by ngxson
9m 27s master
master
9m 27s
llava: Fix cpu-only clip image encoding sefault (#12907) Server #1319: Commit e59ea53 pushed by ngxson
8m 17s master
master
8m 17s
server : add VSCode's Github Copilot Chat support (#12896) Server #1318: Commit c94085d pushed by ngxson
8m 41s master
master
8m 41s
rpc : Set cache directory in rpc-server.cpp on FreeBSD (#12903) Server #1317: Commit e8a6263 pushed by ngxson
9m 4s master
master
9m 4s