Skip to content

Actions: EAddario/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
20 workflow run results
20 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : add RobertaForSequenceClassification reranker support (#13875) CI #20: Commit 6385b84 pushed by EAddario
53m 2s master
master
53m 2s
server: fix streaming crashes (#13786) CI #19: Commit 03f582a pushed by EAddario
57m 1s master
master
57m 1s
server: streaming of tool calls and thoughts when --jinja is on (… CI #18: Commit f5cd27b pushed by EAddario
51m 17s master
master
51m 17s
releases : enable openmp in windows cpu backend build (#13756) CI #17: Commit 17fc817 pushed by EAddario
55m 40s master
master
55m 40s
scripts : fix compare-llama-bench.py show parameter (#13514) CI #16: Commit be1d4a1 pushed by EAddario
59m 52s master
master
59m 52s
docs : Fix typo in InternVL3 model name (#13440) CI #15: Commit 62d4250 pushed by EAddario
55m 15s master
master
55m 15s
llama : move end-user examples to tools directory (#13249) CI #14: Commit 1d36b36 pushed by EAddario
57m 30s master
master
57m 30s
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architectur… CI #13: Commit 5f5e39e pushed by EAddario
49m 58s master
master
49m 58s
llama-bench : Add --override-tensors arg (#12922) CI #12: Commit c0a97b7 pushed by EAddario
44m 28s master
master
44m 28s
llama : fix K-shift with quantized K and BLAS backend (#13113) CI #11: Commit 295354e pushed by EAddario
51m 28s master
master
51m 28s
clip : refactor, add image_manipulation and llava_uhd classes (#1… CI #10: Commit 37b9f0d pushed by EAddario
58m 26s master
master
58m 26s
llama : recognize IBM Granite 3.3 FIM tokens (#12988) CI #9: Commit 971f245 pushed by EAddario
52m 13s master
master
52m 13s
opencl: split ggml-opencl.cl into multiple files and cleanup (#12886) CI #8: Commit 80f19b4 pushed by EAddario
55m 13s master
master
55m 13s
metal : add FA-vec kernels for head size 96 (#12952) CI #7: Commit f8f820c pushed by EAddario
53m 17s master
master
53m 17s
CUDA/HIP: Share the same unified memory allocation logic. (#12934) CI #6: Commit 84778e9 pushed by EAddario
42m 25s master
master
42m 25s
llama : DeepSeek V2/V3 MLA implementation (#12801) CI #5: Commit daa4228 pushed by EAddario
44m 4s master
master
44m 4s
Add performance print for gemma3 in example (#12929) CI #4: Commit d6d2c2a pushed by EAddario
43m 5s master
master
43m 5s
sync : ggml CI #3: Commit 526739b pushed by EAddario
45m 28s master
master
45m 28s
ggml: disable CUDA graphs for unsupported DUP and CONT node types (#1… CI #2: Commit 307bfa2 pushed by EAddario
51m 41s master
master
51m 41s
hellaswag: display estimated score confidence interval (#12797) CI #1: Commit 4ccea21 pushed by EAddario
51m 44s master
master
51m 44s