Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
919 workflow run results
919 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama-bench : Add --override-tensors arg (#12922) Server #1390: Commit c0a97b7 pushed by ngxson
8m 23s master
master
8m 23s
llama-chat : fix wrong template in GLM4-0414 (#13140) Server #1389: Commit ced44be pushed by ngxson
8m 31s master
master
8m 31s
musa: fix build warning (#13129) Server #1388: Commit e291450 pushed by ngxson
8m 49s master
master
8m 49s
Fixes Qwen2.5VL segfault during inference with https://github.com/ggm… Server #1387: Commit 59e991c pushed by ngxson
8m 7s master
master
8m 7s
clip : Add Qwen2.5VL support (#12402) Server #1386: Commit ca2bb89 pushed by ngxson
9m 18s master
master
9m 18s
common : add common_remote_get_content (#13123) Server #1385: Commit 2d451c8 pushed by ngxson
8m 24s master
master
8m 24s
clip : improve projector naming (#13118) Server #1384: Commit 4753791 pushed by ngxson
9m 47s master
master
9m 47s
test windows build curl static Server #1383: Pull request #23 synchronize by ngxson
8m 32s xsn/win_curl_static
xsn/win_curl_static
8m 32s
test windows build curl static Server #1382: Pull request #23 opened by ngxson
9m 39s xsn/win_curl_static
xsn/win_curl_static
9m 39s
ggml: move fp16/bf16 conversion optimizations to CPU backend + export… Server #1381: Commit 77d5e9a pushed by ngxson
8m 28s master
master
8m 28s
common : add common_remote_get_content Server #1380: Commit e6c4319 pushed by ngxson
8m 20s master
master
8m 20s
grammar : handle maxItems == 0 in JSON schema (#13117) Server #1379: Commit d5fe4e8 pushed by ngxson
11m 33s master
master
11m 33s
llama : fix K-shift with quantized K and BLAS backend (#13113) Server #1378: Commit 295354e pushed by ngxson
8m 18s master
master
8m 18s
Force FP32 compute in GLM4 FFN Down (#13101) Server #1377: Commit 558a764 pushed by ngxson
10m 7s master
master
10m 7s
clip : fix pixtral on some GPU backends (#13097) Server #1376: Commit edb18b6 pushed by ngxson
8m 35s master
master
8m 35s
change the reorder tensor from init to execute OP (#13003) Server #1375: Commit 514c456 pushed by ngxson
9m 5s master
master
9m 5s
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943) Server #1374: Commit 553a5c3 pushed by ngxson
9m 39s master
master
9m 39s
clip : remove boi/eoi embeddings for GLM-edge model (#13081) Server #1373: Commit 13be08d pushed by ngxson
8m 18s master
master
8m 18s
embeddings : fix batch sizes (#13076) Server #1372: Commit 226251e pushed by ngxson
8m 31s master
master
8m 31s
ggml : fix trailing whitespaces (#0) Server #1371: Commit 87616f0 pushed by ngxson
8m 38s master
master
8m 38s
CUDA: use switch statements in constexpr functions (#13095) Server #1370: Commit b10d8bf pushed by ngxson
9m 38s master
master
9m 38s
cmake : do not include ./src as public for libllama (#13062) Server #1369: Commit 13b4548 pushed by ngxson
10m 4s master
master
10m 4s
arg : add --no-mmproj-offload (#13093) Server #1368: Commit 7c727fb pushed by ngxson
9m 34s master
master
9m 34s
arg : clean up handling --mmproj with -hf (#13082) Server #1367: Commit 80982e8 pushed by ngxson
10m 19s master
master
10m 19s
vulkan: matmul gcn tuning (#13016) Server #1366: Commit b3b6d86 pushed by ngxson
8m 35s master
master
8m 35s