Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
1,079 workflow run results
1,079 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

minja: sync (qwen3) (#13573) Server #1535: Commit bc098c3 pushed by ngxson
9m 53s master
master
9m 53s
gguf : use ggml log system (#13571) Server #1534: Commit c6a2c9e pushed by ngxson
9m 7s master
master
9m 7s
convert : fix conversion for llama 4 (#13567) Server #1533: Commit c531edf pushed by ngxson
9m 14s master
master
9m 14s
sycl: use oneDNN for matrices multiplication (#12972) Server #1532: Commit 9c404ed pushed by ngxson
9m 22s master
master
9m 22s
llama-bench : fix -ot with dl backends (#13563) Server #1531: Commit 6c8b915 pushed by ngxson
9m 21s master
master
9m 21s
webui : handle PDF input (as text or image) + convert pasted long con… Server #1530: Commit 3cc1f1f pushed by ngxson
9m 17s master
master
9m 17s
server : proper error handling for missing elements in messages array… Server #1529: Commit c753d7b pushed by ngxson
12m 52s master
master
12m 52s
bench : handle decode errors (#13548) Server #1528: Commit b283804 pushed by ngxson
9m 19s master
master
9m 19s
server: inject date_string in llama 3.x template + fix date for fir… Server #1527: Commit aa48e37 pushed by ngxson
17m 13s master
master
17m 13s
arm64: optimize q6_k_q8_k kernel with i8mm (#13519) Server #1526: Commit 5ab5d5f pushed by ngxson
12m 32s master
master
12m 32s
common: add partial regex support (#12808) Server #1525: Commit 3198405 pushed by ngxson
18m 52s master
master
18m 52s
editorconfig : fix trailing whitespace from #13542 (#13546) Server #1524: Commit f5170c1 pushed by ngxson
10m 21s master
master
10m 21s
fix: crash when calling llama_state_get_size on a context without a… Server #1523: Commit 017f10b pushed by ngxson
9m 57s master
master
9m 57s
CUDA: fix crash on large batch size for quant. MoE (#13537) Server #1522: Commit 4696d56 pushed by ngxson
18m 11s master
master
18m 11s
llama : fix quantize with dl backends (#13539) Server #1521: Commit b7d2672 pushed by ngxson
12m 10s master
master
12m 10s
CUDA: faster Deepseek FA, add Turing support (#13435) Server #1520: Commit 6da34fa pushed by ngxson
13m 12s master
master
13m 12s
fix: Move build_inp_pos to the top of the graph section for build_gra… Server #1519: Commit 5e7d95e pushed by ngxson
13m 52s master
master
13m 52s
server : passthrough the /models endpoint during loading (#13535) Server #1518: Commit 0531744 pushed by ngxson
9m 27s master
master
9m 27s
server : fix cache_tokens bug with no cache_prompt (#13533) Server #1517: Commit 360a9c9 pushed by ngxson
14m 31s master
master
14m 31s
cmake: simplify vulkan shader test logic (#13263) Server #1516: Commit 09d13d9 pushed by ngxson
9m 0s master
master
9m 0s
vulkan: KHR_coopmat flash attention (#13506) Server #1515: Commit 24e86ca pushed by ngxson
9m 27s master
master
9m 27s
webui : use fflate for more deterministic gzip compress (#13525) Server #1514: Commit bb1681f pushed by ngxson
9m 49s master
master
9m 49s
webui: Allow pasting file from clipboard (#13526) Server #1513: Commit d486dd3 pushed by ngxson
9m 4s master
master
9m 4s
quantize : improve tensor-type pattern matching (#13033) Server #1512: Commit e5c834f pushed by ngxson
8m 56s master
master
8m 56s
clip : clip.h become private API (⚠️ breaking change) (#13510) Server #1511: Commit 71bdbdb pushed by ngxson
9m 53s master
master
9m 53s