Skip to content

Actions: EAddario/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
79 workflow runs
79 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add support for VK_EXT_debug_utils to add labels to Vulkan objects. (… Server #29: Commit bb16041 pushed by EAddario
10m 13s master
master
10m 13s
sync : ggml Server #28: Commit 06cbedf pushed by EAddario
10m 16s master
master
10m 16s
gguf-py : make sentencepiece optional (#14200) Server #27: Commit 381174b pushed by EAddario
10m 2s master
master
10m 2s
sycl: Cleanup codepaths in Get Rows in sycl backend (#14215) Server #26: Commit 600e3e9 pushed by EAddario
10m 17s master
master
10m 17s
quantize : change int to unsigned int for KV overrides (#14197) Server #25: Commit 30e5b01 pushed by EAddario
11m 12s master
master
11m 12s
kv-cache : fix use-after-move of defrag info (#14189) Server #24: Commit 5fce5f9 pushed by EAddario
10m 57s master
master
10m 57s
compare-llama-bench: add option to plot (#14169) Server #23: Commit 2e42be4 pushed by EAddario
11m 22s master
master
11m 22s
vocab : prevent heap overflow when vocab is too small (#14145) Server #22: Commit c33fe8b pushed by EAddario
18m 15s master
master
18m 15s
docs : add "Quick start" section for new users (#13862) Server #21: Commit ea1431b pushed by EAddario
17m 10s master
master
17m 10s
llama : add RobertaForSequenceClassification reranker support (#13875) Server #20: Commit 6385b84 pushed by EAddario
22m 59s master
master
22m 59s
server: fix streaming crashes (#13786) Server #19: Commit 03f582a pushed by EAddario
10m 13s master
master
10m 13s
server: streaming of tool calls and thoughts when --jinja is on (… Server #18: Commit f5cd27b pushed by EAddario
9m 40s master
master
9m 40s
releases : enable openmp in windows cpu backend build (#13756) Server #17: Commit 17fc817 pushed by EAddario
9m 30s master
master
9m 30s
scripts : fix compare-llama-bench.py show parameter (#13514) Server #16: Commit be1d4a1 pushed by EAddario
11m 27s master
master
11m 27s
docs : Fix typo in InternVL3 model name (#13440) Server #15: Commit 62d4250 pushed by EAddario
8m 39s master
master
8m 39s
llama : move end-user examples to tools directory (#13249) Server #14: Commit 1d36b36 pushed by EAddario
9m 26s master
master
9m 26s
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architectur… Server #13: Commit 5f5e39e pushed by EAddario
9m 22s master
master
9m 22s
llama-bench : Add --override-tensors arg (#12922) Server #12: Commit c0a97b7 pushed by EAddario
12m 29s master
master
12m 29s
llama : fix K-shift with quantized K and BLAS backend (#13113) Server #11: Commit 295354e pushed by EAddario
8m 20s master
master
8m 20s
clip : refactor, add image_manipulation and llava_uhd classes (#1… Server #10: Commit 37b9f0d pushed by EAddario
8m 56s master
master
8m 56s
llama : recognize IBM Granite 3.3 FIM tokens (#12988) Server #9: Commit 971f245 pushed by EAddario
10m 17s master
master
10m 17s
opencl: split ggml-opencl.cl into multiple files and cleanup (#12886) Server #8: Commit 80f19b4 pushed by EAddario
9m 34s master
master
9m 34s
metal : add FA-vec kernels for head size 96 (#12952) Server #7: Commit f8f820c pushed by EAddario
11m 5s master
master
11m 5s
CUDA/HIP: Share the same unified memory allocation logic. (#12934) Server #6: Commit 84778e9 pushed by EAddario
9m 2s master
master
9m 2s
llama : DeepSeek V2/V3 MLA implementation (#12801) Server #5: Commit daa4228 pushed by EAddario
12m 24s master
master
12m 24s