Skip to content

Actions: ServeurpersoCom/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
151 workflow runs
151 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml: add ggml_can_fuse_subgraph (#16662) Server #102: Commit 4926419 pushed by ServeurpersoCom
32m 42s master
master
32m 42s
opencl: fix warnings and clean up profiling (#16688) Server #101: Commit 6ea37f5 pushed by ServeurpersoCom
32m 56s master
master
32m 56s
vulkan: Handle FA with all -inf mask values (#16447) Server #100: Commit fb34984 pushed by ServeurpersoCom
30m 30s master
master
30m 30s
Handle legacy 'context' attachments (#16687) Server #99: Commit c9c1972 pushed by ServeurpersoCom
24m 27s master
master
24m 27s
ggml-alloc : fix leak when reusing a tensor with a larger size (#16679) Server #98: Commit b617cfd pushed by ServeurpersoCom
31m 18s master
master
31m 18s
Import/Export UX improvements (#16619) Server #97: Commit 0e4a0cf pushed by ServeurpersoCom
23m 11s master
master
23m 11s
llama-batch: fix build fails with -Werror=missing-braces (#16614) Server #96: Commit 06332e2 pushed by ServeurpersoCom
16m 35s master
master
16m 35s
llama-context: only warn on pooling_type when user specified (#16674) Server #95: Commit 7062dd8 pushed by ServeurpersoCom
14m 52s master
master
14m 52s
model : add Granite Hybrid types (#16635) Server #94: Commit 0398752 pushed by ServeurpersoCom
33m 1s master
master
33m 1s
HIP: fix GPU_TARGETS (#16642) Server #93: Commit ee09828 pushed by ServeurpersoCom
34m 4s master
master
34m 4s
vulkan: Implement topk_moe fused shader, ported from CUDA (#16641) Server #92: Commit e56abd2 pushed by ServeurpersoCom
34m 20s master
master
34m 20s
CUDA: use registers instead of smem in topk-moe (#16647) Server #91: Commit 38355c6 pushed by ServeurpersoCom
32m 53s master
master
32m 53s
opencl: transposed gemm/gemv moe kernel with mxfp4,f32 (#16602) Server #90: Commit 8138785 pushed by ServeurpersoCom
10m 5s master
master
10m 5s
llama-model: fix insonsistent ctxs <-> bufs order (#16581) Server #89: Commit 66b0dbc pushed by ServeurpersoCom
39m 53s master
master
39m 53s
rpc : report actual free memory (#16616) Server #88: Commit 41386cf pushed by ServeurpersoCom
36m 7s master
master
36m 7s
ggml : fix SpaceMit IME array out-of-bounds in task assignment (#16629) Server #87: Commit 342c728 pushed by ServeurpersoCom
37m 36s master
master
37m 36s
webui: reorganize settings layout (#16607) Server #86: Commit ababae7 pushed by ServeurpersoCom
21m 7s master
master
21m 7s
vulkan: fix debug build (add_rms_len/data not found) (#16624) Server #85: Commit b194915 pushed by ServeurpersoCom
31m 58s master
master
31m 58s
SYCL SET operator optimized for F32 tensors (#16350) Server #84: Commit ceff6bb pushed by ServeurpersoCom
38m 13s master
master
38m 13s
mtmd : support home-cooked Mistral Small Omni (#14928) Server #83: Commit 1bb4f43 pushed by ServeurpersoCom
17m 41s master
master
17m 41s
fix: added a normalization step for MathJax-style \[\] and \(\) delim… Server #82: Commit 683fa6b pushed by ServeurpersoCom
48m 13s master
master
48m 13s
sycl : add ARANGE operator (#16362) Server #81: Commit b22572e pushed by ServeurpersoCom
37m 12s master
master
37m 12s
CANN: format code using .clang-format (#15863) Server #80: Commit 7a50cf3 pushed by ServeurpersoCom
33m 39s master
master
33m 39s
common : Update the docs on -t --threads (#16236) Server #79: Commit 6f5d924 pushed by ServeurpersoCom
29m 30s master
master
29m 30s
SYCL: Add GGML_OP_MEAN operator support (#16009) Server #78: Commit ee50ee1 pushed by ServeurpersoCom
1h 8m 16s master
master
1h 8m 16s