Skip to content

Actions: ggml-org/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
14,474 workflow runs
14,474 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama: store mrope data in KV cell EditorConfig Checker #33156: Pull request #16825 opened by ngxson
1h 33m 59s ngxson:xsn/fix-mrope-causal
ngxson:xsn/fix-mrope-causal
1h 33m 59s
memory : remove KV cache size padding (#16812) EditorConfig Checker #33155: Commit 85a7d86 pushed by ggerganov
1h 16m 52s master
master
1h 16m 52s
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization EditorConfig Checker #33154: Pull request #16653 synchronize by JohannesGaessler
1h 7m 29s JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
1h 7m 29s
Refactor llama-model.cpp EditorConfig Checker #33153: Pull request #16252 synchronize by pwilkin
1h 19m 22s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
1h 19m 22s
llama-bench : clarify benchmarked parts of the computation (#16823) EditorConfig Checker #33152: Commit a8ca18b pushed by ggerganov
51m 19s master
master
51m 19s
llama-bench : clarify benchmarked parts of the computation EditorConfig Checker #33151: Pull request #16823 opened by ggerganov
59m 0s gg/bench-clarify
gg/bench-clarify
59m 0s
CUDA: Fix bug in topk-moe for gpt-oss EditorConfig Checker #33150: Pull request #16821 synchronize by am17an
38m 23s am17an:fix_topk_cuda
am17an:fix_topk_cuda
38m 23s
llama: add linearly increasing token dim for M-RoPE EditorConfig Checker #33149: Pull request #16822 opened by ngxson
1h 20m 8s ngxson:xsn/fix-mrope
ngxson:xsn/fix-mrope
1h 20m 8s
Hexagon Op queue & dispatch optimizations EditorConfig Checker #33148: Pull request #16820 synchronize by max-krasnyansky
1h 36m 35s qualcomm:hexagon-dspqueue-opts
qualcomm:hexagon-dspqueue-opts
1h 36m 35s
CUDA: Fix bug in topk-moe for gpt-oss EditorConfig Checker #33147: Pull request #16821 opened by am17an
1h 39m 31s am17an:fix_topk_cuda
am17an:fix_topk_cuda
1h 39m 31s
Hexagon Op queue & dispatch optimizations EditorConfig Checker #33146: Pull request #16820 opened by max-krasnyansky
10m 23s qualcomm:hexagon-dspqueue-opts
qualcomm:hexagon-dspqueue-opts
10m 23s
server/public_simplechat client ui show reasoning support added, toolcalling with direct builtin tools and beyond also in PR chain EditorConfig Checker #33145: Pull request #16819 opened by hanishkvc
1h 46m 3s hanishkvc:hkvc_server_simplechat_toolcalling_v0420
hanishkvc:hkvc_server_simplechat_toolcalling_v0420
1h 46m 3s
Vulkan MMQ Integer Dot Refactor and K-Quant support EditorConfig Checker #33144: Pull request #16536 synchronize by 0cc4m
1h 21m 16s 0cc4m/vulkan-mmq-dp4a-k-quants
0cc4m/vulkan-mmq-dp4a-k-quants
1h 21m 16s
ggml-cpu: arm64: q4_K repack gemm and gemv implementations (i8mm) EditorConfig Checker #33143: Pull request #16739 synchronize by Alcpz
1h 42m 17s Alcpz:Alcpz/arm_q4_k_repack
Alcpz:Alcpz/arm_q4_k_repack
1h 42m 17s
initialise buffer.device in ggml_hexagon_session (#16816) EditorConfig Checker #33142: Commit 8284efc pushed by max-krasnyansky
1h 3m 7s master
master
1h 3m 7s
[model] add support for qwen3vl series EditorConfig Checker #33141: Pull request #16780 synchronize by JJJYmmm
Action required JJJYmmm:add_qwen3vl
JJJYmmm:add_qwen3vl
Action required
cuda : Add conv2d Implicit GEMM EditorConfig Checker #33140: Pull request #15805 synchronize by bssrdf
3h 21m 53s bssrdf:conv2d-implicit
bssrdf:conv2d-implicit
3h 21m 53s
cuda : Add conv2d Implicit GEMM EditorConfig Checker #33139: Pull request #15805 reopened by bssrdf
1h 50m 28s bssrdf:conv2d-implicit
bssrdf:conv2d-implicit
1h 50m 28s
ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 EditorConfig Checker #33138: Pull request #16805 synchronize by duduta
1h 49m 16s duduta:refactor-rope
duduta:refactor-rope
1h 49m 16s
llama-cli: add support for reasoning EditorConfig Checker #33137: Pull request #16603 synchronize by bandoti
1h 22m 26s bandoti:llamacli-reasoning2
bandoti:llamacli-reasoning2
1h 22m 26s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) EditorConfig Checker #33136: Pull request #16817 opened by yael-works
1h 17m 30s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
1h 17m 30s
[bug fix] initialise buffer.device in ggml_hexagon_session EditorConfig Checker #33135: Pull request #16816 opened by l3utterfly
15m 20s l3utterfly:patch-2
l3utterfly:patch-2
15m 20s
[model] add support for qwen3vl series EditorConfig Checker #33134: Pull request #16780 synchronize by JJJYmmm
Action required JJJYmmm:add_qwen3vl
JJJYmmm:add_qwen3vl
Action required
metal : initial Metal4 tensor API support EditorConfig Checker #33133: Pull request #16634 synchronize by ggerganov
1h 12m 16s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
1h 12m 16s
embedding: add raw option for --embd-output-format (#16541) EditorConfig Checker #33132: Commit 1c1409e pushed by ggerganov
1h 54m 33s master
master
1h 54m 33s