Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
hexagon: matmul and flash-atten scalability updates (#29974) Server #5496: Commit 8345f33 pushed by ngxson
8m 39s master
master
8m 39s
llama.cpp : bump version to 0.6.0 (#29997) Server #5495: Commit d812350 pushed by ngxson
8m 21s master
master
8m 21s
CUDA: make the alloc_deps check batch independent (#29986) Server #5494: Commit e117148 pushed by ngxson
8m 9s master
master
8m 9s
vulkan: fix Flash Attention shmem write out of bounds (#29988) Server #5493: Commit 6c59c40 pushed by ngxson
8m 30s master
master
8m 30s
ci : disable failing test on virtual Metal device (#29993) Server #5492: Commit 8f9ae20 pushed by ngxson
10m 2s master
master
10m 2s
server: reject partial media truncation (#24076) Server #5491: Commit 8e16421 pushed by ngxson
10m 1s master
master
10m 1s
kv-cache: fix restoring mismatched KV cache rotation by saving exact … Server #5490: Commit 2107910 pushed by ngxson
12m 51s master
master
12m 51s
vulkan : Fix undeclared identifiers when -DGGML_VULKAN_RUN_TESTS=ON (… Server #5489: Commit ebe18be pushed by ngxson
7m 5s master
master
7m 5s
metal : few-row MMA mat-mul (#29869) Server #5488: Commit a3a1c47 pushed by ngxson
10m 57s master
master
10m 57s
CUDA: use MMVF for thin f16/bf16 mul_mat at small batch size (#29633) Server #5487: Commit 9d3aba6 pushed by ngxson
8m 36s master
master
8m 36s
log, server: self contained colors, split child commands from logs in… Server #5486: Commit a7fb71f pushed by ngxson
8m 49s master
master
8m 49s
llama: support both embd + raw tokens in batch (#29622) Server #5485: Commit 0bb496d pushed by ngxson
15m 0s master
master
15m 0s
ggml-cpu: support BF16/FP16/FP32 K tails in tinyBLAS on x86 (#29806) Server #5484: Commit a7b94df pushed by ngxson
9m 40s master
master
9m 40s
AGENTS.md : revamp (#29656) Server #5483: Commit bf79dbb pushed by ngxson
7m 57s master
master
7m 57s
ci : set default permissions (#29945) Server #5482: Commit 46847e6 pushed by ngxson
15m 47s master
master
15m 47s
CUDA: fix MMQ memory fault if n_expert >> n_ubatch (#29941) Server #5481: Commit dd26678 pushed by ngxson
12m 21s master
master
12m 21s
imatrix: calculate activation-based statistics for new format (GGUF) … Server #5480: Commit 0504396 pushed by ngxson
9m 1s master
master
9m 1s
webgpu: add f16 support to fill/set_rows (#29897) Server #5479: Commit 11fe021 pushed by ngxson
7m 8s master
master
7m 8s
mtmd : fix deprecated strdup warning on Windows (#29863) Server #5478: Commit 836d571 pushed by ngxson
8m 10s master
master
8m 10s
vendor : update cpp-httplib to 0.59.0 (#29886) Server #5477: Commit eec18f5 pushed by ngxson
14m 28s master
master
14m 28s
server : fix laya abort by limiting n_batch to n_ubatch (#29903) Server #5476: Commit 1537a0a pushed by ngxson
7m 51s master
master
7m 51s
common : add common_is_tty() helper and fix deprecated warnings on Wi… Server #5475: Commit edd6e2b pushed by ngxson
14m 54s master
master
14m 54s
ci: fix flaky ADD_ADD f16 by using the fused ADD tolerance (#29904) Server #5474: Commit a55e952 pushed by ngxson
7m 29s master
master
7m 29s
graph: gather the recurrent states once so the reserve covers every s… Server #5473: Commit 436f6f8 pushed by ngxson
13m 44s master
master
13m 44s
ggml-openvino: update to 2026.4.1, optimize performance, expand ops, … Server #5472: Commit b92761a pushed by ngxson
12m 20s master
master
12m 20s