Skip to content

Actions: ngxson/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
975 workflow run results
975 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CANN: Add x86 build ci (#12950) CI #1220: Commit 54a7272 pushed by ngxson
51m 9s master
master
51m 9s
CUDA/HIP: Share the same unified memory allocation logic. (#12934) CI #1219: Commit 84778e9 pushed by ngxson
46m 34s master
master
46m 34s
SYCL: Add ROPE vision kernel (#12887) CI #1218: Commit 5106764 pushed by ngxson
42m 16s master
master
42m 16s
llama : DeepSeek V2/V3 MLA implementation (#12801) CI #1217: Commit daa4228 pushed by ngxson
46m 38s master
master
46m 38s
ggml : Add AVX512 implementation of GEMM - Q4_Kx8 (#12829) CI #1216: Commit eccc7a1 pushed by ngxson
47m 7s master
master
47m 7s
CANN: Opt ROPE optimization (#12865) CI #1215: Commit 0019279 pushed by ngxson
55m 42s master
master
55m 42s
CANN: Optimize CANN buffer pool memory management (#12875) CI #1214: Commit b0c75ac pushed by ngxson
42m 56s master
master
42m 56s
Add performance print for gemma3 in example (#12929) CI #1213: Commit d6d2c2a pushed by ngxson
43m 26s master
master
43m 26s
SYCL: Fix im2col (#12910) CI #1212: Commit 75afa0a pushed by ngxson
43m 44s master
master
43m 44s
rpc : use ggml_context_ptr (#12938) CI #1211: Commit c772d54 pushed by ngxson
47m 2s master
master
47m 2s
sync : ggml CI #1210: Commit 526739b pushed by ngxson
44m 46s master
master
44m 46s
ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into… CI #1209: Commit e959d32 pushed by ngxson
50m 14s master
master
50m 14s
ggml: disable CUDA graphs for unsupported DUP and CONT node types (#1… CI #1208: Commit 307bfa2 pushed by ngxson
41m 2s master
master
41m 2s
quantize: Handle user-defined quantization levels for additional tens… CI #1207: Commit 71e90e8 pushed by ngxson
49m 34s master
master
49m 34s
common : Define cache directory on AIX (#12915) CI #1206: Commit bc091a4 pushed by ngxson
42m 57s master
master
42m 57s
vulkan: use aligned loads for flash attention mask (#12853) CI #1205: Commit a483757 pushed by ngxson
49m 48s master
master
49m 48s
llava: Fix cpu-only clip image encoding sefault (#12907) CI #1204: Commit e59ea53 pushed by ngxson
46m 36s master
master
46m 36s
server : add VSCode's Github Copilot Chat support (#12896) CI #1203: Commit c94085d pushed by ngxson
48m 32s master
master
48m 32s
rpc : Set cache directory in rpc-server.cpp on FreeBSD (#12903) CI #1202: Commit e8a6263 pushed by ngxson
57m 43s master
master
57m 43s
tool-call: fix non-tool-calling grammar crashes w/ Qwen / Hermes 2 … CI #1201: Commit b6930eb pushed by ngxson
49m 56s master
master
49m 56s
sycl: Support sycl_ext_oneapi_limited_graph (#12873) CI #1200: Commit 578754b pushed by ngxson
49m 7s master
master
49m 7s
contrib: support modelscope community (#12664) CI #1199: Commit b2034c2 pushed by ngxson
44m 59s master
master
44m 59s
llama-model : add Glm4Model implementation for GLM-4-0414 (#12867) CI #1198: Commit 06bb53a pushed by ngxson
49m 40s master
master
49m 40s
SYCL: Add fp16 type support to unary op kernels (#12788) CI #1197: Commit fccf9ca pushed by ngxson
44m 13s master
master
44m 13s
llama : correct rms norm for llama 4 (#12882) CI #1196: Commit 8b91d53 pushed by ngxson
44m 39s master
master
44m 39s