Skip to content

Actions: ngxson/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
419 workflow run results
419 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : implement cancellable request (#11285) CI #715: Commit f30f099 pushed by ngxson
42m 25s master
master
42m 25s
tts : add guide tokens support (#11186) CI #714: Commit 6390a99 pushed by ngxson
38m 19s master
master
38m 19s
vulkan: fix coopmat2 flash attention for non-contiguous inputs (#11281) CI #713: Commit 44e18ef pushed by ngxson
32m 20s master
master
32m 20s
llama.android: add field formatChat to control whether to parse speci… CI #712: Commit 3edfa7d pushed by ngxson
43m 36s master
master
43m 36s
rpc : early register backend devices (#11262) CI #711: Commit 667d728 pushed by ngxson
42m 14s master
master
42m 14s
vocab : fix double-eos check (#11273) CI #710: Commit a133566 pushed by ngxson
42m 47s master
master
42m 47s
llama : fix deprecation message: vocabable -> vocab (#11269) CI #709: Commit 960ec65 pushed by ngxson
39m 56s master
master
39m 56s
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (#11… CI #708: Commit bd38dde pushed by ngxson
37m 48s master
master
37m 48s
CUDA: backwards pass for misc. ops, add tests (#11257) CI #707: Commit 9c8dcef pushed by ngxson
52m 20s master
master
52m 20s
llama : add llama_model_load_from_splits (#11255) CI #706: Commit 681149c pushed by ngxson
39m 17s master
master
39m 17s
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227) CI #705: Commit c67cc98 pushed by ngxson
1h 9m 30s master
master
1h 9m 30s
fix: ggml: fix vulkan-shaders-gen build (#10448) CI #704: Commit 1d85043 pushed by ngxson
36m 19s master
master
36m 19s
RoPE: fix back, CUDA support for back + noncont. (#11240) CI #703: Commit 432df2d pushed by ngxson
45m 18s master
master
45m 18s
SYCL: Add gated linear attention kernel (#11175) CI #702: Commit f446c2c pushed by ngxson
46m 49s master
master
46m 49s
Refactor test-chat-template.cpp (#11224) CI #701: Commit 091592d pushed by ngxson
37m 0s master
master
37m 0s
cli : auto activate conversation mode if chat template is available (… CI #700: Commit 84a4481 pushed by ngxson
40m 0s master
master
40m 0s
cuda : CUDA Graph Compute Function Refactor (precursor for performanc… CI #699: Commit 39509fb pushed by ngxson
38m 52s master
master
38m 52s
common : support tag-based --hf-repo like on ollama (#11195) CI #698: Commit 00b4c3d pushed by ngxson
45m 53s master
master
45m 53s
llama : remove 'd' from bad special token log (#11212) CI #697: Commit 8f70fc3 pushed by ngxson
40m 42s master
master
40m 42s
ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL… CI #696: Commit 1244cdc pushed by ngxson
37m 24s master
master
37m 24s
Reset color before we exit (#11205) CI #695: Commit 924518e pushed by ngxson
34m 39s master
master
34m 39s
llama : fix chat template gguf key (#11201) CI #694: Commit 9a48399 pushed by ngxson
38m 1s master
master
38m 1s
llama : remove notion of CLS token (#11064) CI #693: Commit 08f10f6 pushed by ngxson
43m 7s master
master
43m 7s
Vulkan: Fix float16 use on devices without float16 support + fix subg… CI #692: Commit c3f9d25 pushed by ngxson
43m 10s master
master
43m 10s
llama: add support for QRWKV6 model architecture (#11001) CI #691: Commit ee7136c pushed by ngxson
45m 59s master
master
45m 59s