Skip to content

Actions: ngxson/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
3,168 workflow run results
3,168 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : upgrade init_tensor API to return a ggml_status (#11854) CI #918: Commit 70680c4 pushed by ngxson
50m 19s master
master
50m 19s
ggml : upgrade init_tensor API to return a ggml_status (#11854) Server #1044: Commit 70680c4 pushed by ngxson
7m 45s master
master
7m 45s
llama : add Phi-4-mini support (supersede #12099) (#12108) Python check requirements.txt #207: Commit c43a3e7 pushed by ngxson
2m 28s master
master
2m 28s
llama : add Phi-4-mini support (supersede #12099) (#12108) Python Type-Check #290: Commit c43a3e7 pushed by ngxson
1m 8s master
master
1m 8s
llama : add Phi-4-mini support (supersede #12099) (#12108) EditorConfig Checker #1120: Commit c43a3e7 pushed by ngxson
22s master
master
22s
llama : add Phi-4-mini support (supersede #12099) (#12108) flake8 Lint #1215: Commit c43a3e7 pushed by ngxson
22s master
master
22s
llama : add Phi-4-mini support (supersede #12099) (#12108) Server #1043: Commit c43a3e7 pushed by ngxson
8m 24s master
master
8m 24s
llama : add Phi-4-mini support (supersede #12099) (#12108) CI #917: Commit c43a3e7 pushed by ngxson
47m 42s master
master
47m 42s
Update granite vision docs for 3.2 model (#12105) EditorConfig Checker #1119: Commit 84d5f4b pushed by ngxson
23s master
master
23s
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizatio… CI #916: Commit 438a839 pushed by ngxson
41m 6s master
master
41m 6s
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizatio… Server #1042: Commit 438a839 pushed by ngxson
8m 55s master
master
8m 55s
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizatio… EditorConfig Checker #1118: Commit 438a839 pushed by ngxson
19s master
master
19s
CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ (#12098) EditorConfig Checker #1117: Commit 9c42b17 pushed by ngxson
22s master
master
22s
CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ (#12098) CI #915: Commit 9c42b17 pushed by ngxson
36m 5s master
master
36m 5s
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064) EditorConfig Checker #1116: Commit 05e6f5a pushed by ngxson
24s master
master
24s
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064) CI #914: Commit 05e6f5a pushed by ngxson
52m 9s master
master
52m 9s
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064) Server #1041: Commit 05e6f5a pushed by ngxson
24m 7s master
master
24m 7s
CANN: Fix build error with GCC 13 (#11990) Server #1040: Commit 673cfef pushed by ngxson
10m 48s master
master
10m 48s
CANN: Fix build error with GCC 13 (#11990) EditorConfig Checker #1115: Commit 673cfef pushed by ngxson
2m 44s master
master
2m 44s
CANN: Fix build error with GCC 13 (#11990) CI #913: Commit 673cfef pushed by ngxson
44m 12s master
master
44m 12s
vulkan: matmul dequantization improvements (#12015) Server #1039: Commit fbeda90 pushed by ngxson
7m 44s master
master
7m 44s
vulkan: matmul dequantization improvements (#12015) EditorConfig Checker #1114: Commit fbeda90 pushed by ngxson
21s master
master
21s
vulkan: matmul dequantization improvements (#12015) CI #912: Commit fbeda90 pushed by ngxson
45m 28s master
master
45m 28s
vulkan: improve im2col (#11826) CI #911: Commit 581650b pushed by ngxson
36m 43s master
master
36m 43s
vulkan: improve im2col (#11826) EditorConfig Checker #1113: Commit 581650b pushed by ngxson
22s master
master
22s