Skip to content

Actions: ServeurpersoCom/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
137 workflow run results
137 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: Handle FA with all -inf mask values (#16447) CI #87: Commit fb34984 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
ggml-alloc : fix leak when reusing a tensor with a larger size (#16679) CI #86: Commit b617cfd pushed by ServeurpersoCom
1d 0h 0m 8s master
master
1d 0h 0m 8s
llama-batch: fix build fails with -Werror=missing-braces (#16614) CI #85: Commit 06332e2 pushed by ServeurpersoCom
1d 0h 0m 4s master
master
1d 0h 0m 4s
llama-context: only warn on pooling_type when user specified (#16674) CI #84: Commit 7062dd8 pushed by ServeurpersoCom
1d 0h 0m 5s master
master
1d 0h 0m 5s
model : add Granite Hybrid types (#16635) CI #83: Commit 0398752 pushed by ServeurpersoCom
1d 0h 0m 4s master
master
1d 0h 0m 4s
HIP: fix GPU_TARGETS (#16642) CI #82: Commit ee09828 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
vulkan: Implement topk_moe fused shader, ported from CUDA (#16641) CI #81: Commit e56abd2 pushed by ServeurpersoCom
1d 0h 0m 4s master
master
1d 0h 0m 4s
CUDA: use registers instead of smem in topk-moe (#16647) CI #80: Commit 38355c6 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
opencl: transposed gemm/gemv moe kernel with mxfp4,f32 (#16602) CI #79: Commit 8138785 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
llama-model: fix insonsistent ctxs <-> bufs order (#16581) CI #78: Commit 66b0dbc pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
rpc : report actual free memory (#16616) CI #77: Commit 41386cf pushed by ServeurpersoCom
1d 0h 0m 2s master
master
1d 0h 0m 2s
ggml : fix SpaceMit IME array out-of-bounds in task assignment (#16629) CI #76: Commit 342c728 pushed by ServeurpersoCom
1d 0h 0m 5s master
master
1d 0h 0m 5s
vulkan: fix debug build (add_rms_len/data not found) (#16624) CI #75: Commit b194915 pushed by ServeurpersoCom
1d 0h 0m 4s master
master
1d 0h 0m 4s
SYCL SET operator optimized for F32 tensors (#16350) CI #74: Commit ceff6bb pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
mtmd : support home-cooked Mistral Small Omni (#14928) CI #73: Commit 1bb4f43 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
sycl : add ARANGE operator (#16362) CI #72: Commit b22572e pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
CANN: format code using .clang-format (#15863) CI #71: Commit 7a50cf3 pushed by ServeurpersoCom
1d 0h 0m 5s master
master
1d 0h 0m 5s
common : Update the docs on -t --threads (#16236) CI #70: Commit 6f5d924 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
SYCL: Add GGML_OP_MEAN operator support (#16009) CI #69: Commit ee50ee1 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s
gguf-py : add support for endian conversion of BF16 data (#16594) CI #68: Commit 7adc79c pushed by ServeurpersoCom
1d 0h 0m 5s master
master
1d 0h 0m 5s
opencl: add q8_0 mm support (#16469) CI #67: Commit 0cb7a06 pushed by ServeurpersoCom
1d 0h 0m 4s master
master
1d 0h 0m 4s
Add server-driven parameter defaults and syncing (#16515) CI #66: Commit f9fb33f pushed by ServeurpersoCom
1d 0h 0m 6s master
master
1d 0h 0m 6s
CUDA: Changing the CUDA scheduling strategy to spin (#16585) CI #65: Commit 5acd455 pushed by ServeurpersoCom
1d 0h 0m 6s master
master
1d 0h 0m 6s
metal : avoid using Metal's gpuAddress property (#16576) CI #64: Commit fa882fd pushed by ServeurpersoCom
1d 0h 0m 2s master
master
1d 0h 0m 2s
vulkan: Add ACC_TYPE_VEC2 implementation (#16203) CI #63: Commit ffa0590 pushed by ServeurpersoCom
1d 0h 0m 3s master
master
1d 0h 0m 3s