Skip to content

Actions: rmatif/llama.cpp

Actions

Python Type-Check

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-type-check.yml
18 workflow runs
18 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix FA rowsum/offset Python Type-Check #18: Commit 23be8be pushed by rmatif
2m 9s cuda-fa-fixes
cuda-fa-fixes
2m 9s
llama : set n_outputs to 1 to avoid 0 outputs mean-pooling (#15791) Python Type-Check #17: Commit d1e2adb pushed by rmatif
1m 59s vk-mulmat-embed
vk-mulmat-embed
1m 59s
fix: resolve unsigned int initialization warning for n_dims/size in g… Python Type-Check #16: Commit 3de0082 pushed by rmatif
1m 49s master
master
1m 49s
fix trailing whitespace Python Type-Check #15: Commit 67bb486 pushed by rmatif
12m 10s opencl-add-fused-norms
opencl-add-fused-norms
12m 10s
CUDA: Accelerate MXFP4 table lookup using __byte_perm (#15451) Python Type-Check #14: Commit 74f52f7 pushed by rmatif
2m 19s master
master
2m 19s
bump GGML_OP_COUNT Python Type-Check #13: Commit 9162cd4 pushed by rmatif
1m 29s add-conv3d
add-conv3d
1m 29s
llama : remove KV cache defragmentation logic (#15473) Python Type-Check #12: Commit 9ebebef pushed by rmatif
2m 6s master
master
2m 6s
vulkan: perf_logger improvements (#15246) Python Type-Check #11: Commit 863d341 pushed by rmatif
1m 41s opencl-add-fused-norms
opencl-add-fused-norms
1m 41s
ggml : fix field name when new ggml_backend (#14944) Python Type-Check #10: Commit cd6983d pushed by rmatif
1m 36s add-conv3d
add-conv3d
1m 36s
opencl: add swiglu_oai and add_id (#15121) Python Type-Check #9: Commit e725a1a pushed by rmatif
1m 36s opencl-mixed-add
opencl-mixed-add
1m 36s
vulkan: fix build when using glslang that does not support coopmat2 (… Python Type-Check #8: Commit 5aa1105 pushed by rmatif
9m 27s master
master
9m 27s
opencl: fix adreno compiler detection logic (#15029) Python Type-Check #7: Commit 5c0eb5e pushed by rmatif
1m 36s opencl-fix-profiling
opencl-fix-profiling
1m 36s
Add LLaDA 8b Diffusion model (#14771) Python Type-Check #6: Commit 8a4a856 pushed by rmatif
1m 41s opencl-add-fa
opencl-add-fa
1m 41s
handle f16 input and f16 kernel, more opt Python Type-Check #5: Commit 8412441 pushed by rmatif
1m 27s opencl-add-conv2d
opencl-add-conv2d
1m 27s
batch : add optional for sequential equal split (#14511) Python Type-Check #4: Commit 67d1ef2 pushed by rmatif
1m 28s opencl-add-tiled-mul-mat-f16-f32
opencl-add-tiled-mul-mat-f16-f32
1m 28s
model : gemma3n text-only (#14400) Python Type-Check #3: Commit 8846aac pushed by rmatif
1m 33s master
master
1m 33s
llama : return mistral-v7-tekken as default template only (#14390) Python Type-Check #2: Commit b253462 pushed by rmatif
1m 51s master
master
1m 51s
llama : return mistral-v7-tekken as default template only (#14390) Python Type-Check #1: Commit b253462 pushed by rmatif
1m 53s opencl-add-conv2d
opencl-add-conv2d
1m 53s