Skip to content

Actions: timkhronos/llama.cpp

Actions

Release

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
release.yml
11 workflow runs
11 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
ggml-cuda : disable MMQ on devices with less than 48 KiB shared memor… Release #11: Commit caa596a pushed by timkhronos
1d 0h 18m 16s master
master
1d 0h 18m 16s
fit : count nextn (MTP) blocks in n_gpu_layers so front layers stay o… Release #10: Commit 0324696 pushed by timkhronos
1d 23h 24m 53s master
master
1d 23h 24m 53s
sycl(build): parallelize ocloc invocations (#25903) Release #9: Commit 8e8681e pushed by timkhronos
1d 0h 10m 38s master
master
1d 0h 10m 38s
cuda : prevent integer truncation and overflow errors when using KQ m… Release #8: Commit 0eca4d4 pushed by timkhronos
1d 0h 12m 58s master
master
1d 0h 12m 58s
[SYCL] support bf16 on bin_bcast OP and unary OPs (#24838) Release #7: Commit f8cc15f pushed by timkhronos
1d 0h 15m 28s master
master
1d 0h 15m 28s
Update clip.cpp Release #6: Commit 783ba88 pushed by timkhronos
Failure minimax-m3-vision
minimax-m3-vision
Failure
llama : skip main_gpu validation when no devices are available (#23405) Release #5: Commit b4024af pushed by timkhronos
1d 1h 38m 39s master
master
1d 1h 38m 39s
Delete m3_vision_ref.py Release #4: Commit 64624a5 pushed by timkhronos
Failure minimax-m3-vision
minimax-m3-vision
Failure
MiniMax-M3 vision tower (mmproj + clip graph) Release #3: Commit 0c8c13c pushed by timkhronos
Failure minimax-m3-vision
minimax-m3-vision
Failure
ui: add source toggle to mermaid and svg blocks (#24652) Release #2: Commit c1304d7 pushed by timkhronos
1d 0h 9m 52s master
master
1d 0h 9m 52s
CUDA: Check PTX version on host side to guard PDL dispatch (#23530) Release #1: Commit 6ed481e pushed by timkhronos
1d 0h 4m 7s master
master
1d 0h 4m 7s