Skip to content

Actions: ngxson/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
3,639 workflow run results
3,639 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : add SVE support for q6_K_q8_K (#12361) EditorConfig Checker #1230: Commit d9a1452 pushed by ngxson
17s master
master
17s
ggml : add SVE support for q6_K_q8_K (#12361) Server #1135: Commit d9a1452 pushed by ngxson
11m 18s master
master
11m 18s
Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentat… CI #1014: Commit fd123cf pushed by ngxson
45m 6s master
master
45m 6s
Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentat… Server #1134: Commit fd123cf pushed by ngxson
9m 50s master
master
9m 50s
Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentat… EditorConfig Checker #1229: Commit fd123cf pushed by ngxson
20s master
master
20s
Publish Docker image Publish Docker image #651: Scheduled
41m 0s master
master
41m 0s
Close inactive issues Close inactive issues #364: Scheduled
9s master
master
9s
fixed compilation warnings in ggml-sycl (#12424) Server #1133: Commit a53f7f7 pushed by ngxson
10m 24s master
master
10m 24s
fixed compilation warnings in ggml-sycl (#12424) EditorConfig Checker #1228: Commit a53f7f7 pushed by ngxson
19s master
master
19s
fixed compilation warnings in ggml-sycl (#12424) CI #1013: Commit a53f7f7 pushed by ngxson
44m 43s master
master
44m 43s
llama: Add support for RWKV v7 architecture (#12412) Server #1132: Commit 7dfad38 pushed by ngxson
19m 52s master
master
19m 52s
llama: Add support for RWKV v7 architecture (#12412) flake8 Lint #1225: Commit 7dfad38 pushed by ngxson
17s master
master
17s
llama: Add support for RWKV v7 architecture (#12412) EditorConfig Checker #1227: Commit 7dfad38 pushed by ngxson
18s master
master
18s
llama: Add support for RWKV v7 architecture (#12412) CI #1012: Commit 7dfad38 pushed by ngxson
55m 36s master
master
55m 36s
llama: Add support for RWKV v7 architecture (#12412) Python Type-Check #314: Commit 7dfad38 pushed by ngxson
1m 22s master
master
1m 22s
llama: Add support for RWKV v7 architecture (#12412) Python check requirements.txt #218: Commit 7dfad38 pushed by ngxson
2m 38s master
master
2m 38s
docs : bring llama-cli conversation/template docs up-to-date (#12426) EditorConfig Checker #1226: Commit 60c9029 pushed by ngxson
17s master
master
17s
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394) Server #1131: Commit b1b132e pushed by ngxson
8m 2s master
master
8m 2s
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394) EditorConfig Checker #1225: Commit b1b132e pushed by ngxson
19s master
master
19s
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394) CI #1011: Commit b1b132e pushed by ngxson
53m 17s master
master
53m 17s
ggml-vulkan: remove unused find_program(glslc) (#12416) CI #1010: Commit 01e8f21 pushed by ngxson
43m 31s master
master
43m 31s
ggml-vulkan: remove unused find_program(glslc) (#12416) EditorConfig Checker #1224: Commit 01e8f21 pushed by ngxson
18s master
master
18s
ggml-vulkan: remove unused find_program(glslc) (#12416) Server #1130: Commit 01e8f21 pushed by ngxson
11m 49s master
master
11m 49s
vulkan: Add N/2 and N/4 optimized paths in coopmat2 shader (#12312) CI #1009: Commit 484a8ab pushed by ngxson
45m 25s master
master
45m 25s
vulkan: Add N/2 and N/4 optimized paths in coopmat2 shader (#12312) Server #1129: Commit 484a8ab pushed by ngxson
8m 13s master
master
8m 13s