Skip to content

Actions: janhq/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
136 workflow run results
136 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan : add fp16 support for the conv_2d kernel (#14872) EditorConfig Checker #136: Commit 89d1029 pushed by jan-service-account
17s master
master
17s
HIP: Enable Matrix cores for MMQ Kernels, Enable stream-K for CDNA 3 … EditorConfig Checker #135: Commit 66906cd pushed by jan-service-account
21s master
master
21s
ggml-cpu : disable GGML_NNPA by default due to instability (#14880) EditorConfig Checker #134: Commit c7f3169 pushed by jan-service-account
17s master
master
17s
musa: upgrade musa sdk to rc4.2.0 (#14498) EditorConfig Checker #133: Commit 3f4fc97 pushed by jan-service-account
18s master
master
18s
CUDA: fix overflow in FA, tune performance (#14840) EditorConfig Checker #132: Commit a86f52b pushed by jan-service-account
16s master
master
16s
vulkan: fix rms_norm_mul to handle broadcasting dim0 (#14817) EditorConfig Checker #131: Commit 84712b6 pushed by jan-service-account
17s master
master
17s
server : allow setting --reverse-prompt arg (#14799) EditorConfig Checker #130: Commit adef817 pushed by jan-service-account
17s master
master
17s
ggml: adds CONV_2D op and direct GEMM Vulkan implementation (#14316) EditorConfig Checker #129: Commit a979ca2 pushed by jan-service-account
17s master
master
17s
metal : fuse add, mul + add tests (#14596) EditorConfig Checker #128: Commit bf9087f pushed by jan-service-account
17s master
master
17s
model: add Ernie 4.5 MoE support (#14658) EditorConfig Checker #127: Commit cb887f1 pushed by jan-service-account
17s master
master
17s
llama : fix parameter order for hybrid memory initialization (#14725) EditorConfig Checker #126: Commit 496957e pushed by jan-service-account
18s master
master
18s
model : add Kimi-K2 support (#14654) EditorConfig Checker #125: Commit 4a4f426 pushed by jan-service-account
18s master
master
18s
llama : add jinja template for rwkv-world (#14665) EditorConfig Checker #124: Commit 0d92267 pushed by jan-service-account
16s master
master
16s
tests : cover lfm2 cases in test_ssm_conv (#14651) EditorConfig Checker #123: Commit c31e606 pushed by jan-service-account
16s master
master
16s
model : support LiquidAI LFM2 hybrid family (#14620) EditorConfig Checker #122: Commit f5e96b3 pushed by jan-service-account
22s master
master
22s
opencl: add tiled mul_mat_f16_f32 (#14535) EditorConfig Checker #121: Commit 6bdda13 pushed by jan-service-account
19s master
master
19s
llama : remove llm_graph_input_one (#14603) EditorConfig Checker #120: Commit cb9178f pushed by jan-service-account
19s master
master
19s
vulkan: optimize flash attention split_k_reduce (#14554) EditorConfig Checker #119: Commit 6efcd65 pushed by jan-service-account
17s master
master
17s
llama : fix incorrect minicpm3 v_states shape (#14571) EditorConfig Checker #118: Commit e1a7059 pushed by jan-service-account
15s master
master
15s
vulkan: increase LOAD_VEC_A to 8 (IQ1/IQ2) or 4 (IQ3) (#14485) EditorConfig Checker #117: Commit 6491d6e pushed by jan-service-account
19s master
master
19s
vulkan: Handle updated FA dim2/3 definition (#14518) EditorConfig Checker #116: Commit a0374a6 pushed by jan-service-account
18s master
master
18s
metal : disable fast math in all quantize kernels (#14528) EditorConfig Checker #115: Commit ef797db pushed by jan-service-account
16s master
master
16s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445) EditorConfig Checker #114: Commit 28657a8 pushed by jan-service-account
20s master
master
20s
llama : initial Mamba-2 support (#9126) EditorConfig Checker #113: Commit 5d46bab pushed by jan-service-account
21s master
master
21s
ggml : Callback before abort (#14481) EditorConfig Checker #112: Commit 68b3cd6 pushed by jan-service-account
20s master
master
20s