Skip to content

Actions: EAddario/llama.cpp

Actions

flake8 Lint

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-lint.yml
41 workflow run results
41 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

compare-llama-bench: add option to plot (#14169) flake8 Lint #16: Commit 2e42be4 pushed by EAddario
19s master
master
19s
vocab : prevent heap overflow when vocab is too small (#14145) flake8 Lint #15: Commit c33fe8b pushed by EAddario
15s master
master
15s
docs : add "Quick start" section for new users (#13862) flake8 Lint #14: Commit ea1431b pushed by EAddario
21s master
master
21s
llama : add RobertaForSequenceClassification reranker support (#13875) flake8 Lint #13: Commit 6385b84 pushed by EAddario
15s master
master
15s
server: fix streaming crashes (#13786) flake8 Lint #12: Commit 03f582a pushed by EAddario
16s master
master
16s
server: streaming of tool calls and thoughts when --jinja is on (… flake8 Lint #11: Commit f5cd27b pushed by EAddario
19s master
master
19s
releases : enable openmp in windows cpu backend build (#13756) flake8 Lint #10: Commit 17fc817 pushed by EAddario
15s master
master
15s
scripts : fix compare-llama-bench.py show parameter (#13514) flake8 Lint #9: Commit be1d4a1 pushed by EAddario
19s master
master
19s
docs : Fix typo in InternVL3 model name (#13440) flake8 Lint #8: Commit 62d4250 pushed by EAddario
15s master
master
15s
llama : move end-user examples to tools directory (#13249) flake8 Lint #7: Commit 1d36b36 pushed by EAddario
16s master
master
16s
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architectur… flake8 Lint #6: Commit 5f5e39e pushed by EAddario
14s master
master
14s
llama-bench : Add --override-tensors arg (#12922) flake8 Lint #5: Commit c0a97b7 pushed by EAddario
16s master
master
16s
llama : fix K-shift with quantized K and BLAS backend (#13113) flake8 Lint #4: Commit 295354e pushed by EAddario
15s master
master
15s
clip : refactor, add image_manipulation and llava_uhd classes (#1… flake8 Lint #3: Commit 37b9f0d pushed by EAddario
17s master
master
17s
llama : DeepSeek V2/V3 MLA implementation (#12801) flake8 Lint #2: Commit daa4228 pushed by EAddario
17s master
master
17s
ggml: disable CUDA graphs for unsupported DUP and CONT node types (#1… flake8 Lint #1: Commit 307bfa2 pushed by EAddario
3m 1s master
master
3m 1s