Skip to content

Actions: janhq/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
36 workflow run results
36 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

graph : make FA compatible with MLA + add initial Metal kernels (#12953) EditorConfig Checker #36: Commit 2f74c35 pushed by jan-service-account
19s master
master
19s
opencl: fix incorrect local_size index in profiling log (#12868) EditorConfig Checker #35: Commit 12b1750 pushed by jan-service-account
24s master
master
24s
opencl: split ggml-opencl.cl into multiple files and cleanup (#12886) EditorConfig Checker #34: Commit 80f19b4 pushed by jan-service-account
21s master
master
21s
Add performance print for gemma3 in example (#12929) EditorConfig Checker #33: Commit d6d2c2a pushed by jan-service-account
19s master
master
19s
ggml: disable CUDA graphs for unsupported DUP and CONT node types (#1… EditorConfig Checker #32: Commit 307bfa2 pushed by jan-service-account
23s master
master
23s
common : Define cache directory on AIX (#12915) EditorConfig Checker #31: Commit bc091a4 pushed by jan-service-account
22s master
master
22s
server : add VSCode's Github Copilot Chat support (#12896) EditorConfig Checker #30: Commit c94085d pushed by jan-service-account
21s master
master
21s
sync : ggml EditorConfig Checker #29: Commit 47ba87d pushed by jan-service-account
19s master
master
19s
ggml-impl.h: fix build on POWER9 (#12855) EditorConfig Checker #28: Commit 2391506 pushed by jan-service-account
22s master
master
22s
cuda : add f32 to bf16 copy op (#12806) EditorConfig Checker #27: Commit 7538246 pushed by jan-service-account
21s master
master
21s
llama : Support llama 4 text-only (#12791) EditorConfig Checker #26: Commit 1466621 pushed by jan-service-account
21s master
master
21s
musa: fix compilation warnings in mp_22/31 (#12780) EditorConfig Checker #25: Commit 916c83b pushed by jan-service-account
19s master
master
19s
Vulkan: Tune Vulkan mmq int dot shader for performance (#12767) EditorConfig Checker #24: Commit 6bf28f0 pushed by jan-service-account
23s master
master
23s
sync: minja (#12739) EditorConfig Checker #23: Commit 7a84777 pushed by jan-service-account
23s master
master
23s
CUDA: Prefer vector flash decoding kernel for Gemma models (#12738) EditorConfig Checker #22: Commit c262bed pushed by jan-service-account
18s master
master
18s
vulkan: Implement split_k for coopmat2 flash attention. (#12627) EditorConfig Checker #21: Commit f01bd02 pushed by jan-service-account
18s master
master
18s
opencl : fix memory allocation size (#12649) EditorConfig Checker #20: Commit f423981 pushed by jan-service-account
20s master
master
20s
vocab : add special infill tokens for CodeLlama (#11850) EditorConfig Checker #19: Commit c80a775 pushed by jan-service-account
20s master
master
20s
llama : support BailingMoE (Ling) (#12634) EditorConfig Checker #18: Commit 2c3f8b8 pushed by jan-service-account
26s master
master
26s
llama : fix non-causal mask for gemma 3 (#12615) EditorConfig Checker #17: Commit af6ae1e pushed by jan-service-account
23s master
master
23s
llama : fix incorrect Qwen2Moe ffn_moe_out graph callback (#12631) EditorConfig Checker #16: Commit 3714c3e pushed by jan-service-account
19s master
master
19s
server : Support listening on a unix socket (#12613) EditorConfig Checker #15: Commit 2099a9d pushed by jan-service-account
25s master
master
25s
HIP: Add support for RDNA4 targets (#12372) EditorConfig Checker #14: Commit bd40678 pushed by jan-service-account
21s master
master
21s
run: de-duplicate fmt and format functions and optimize (#11596) EditorConfig Checker #13: Commit ef19c71 pushed by jan-service-account
18s master
master
18s
opencl: simplify kernel embedding logic in cmakefile (#12503) EditorConfig Checker #12: Commit 2b65ae3 pushed by jan-service-account
20s master
master
20s