Skip to content

Actions: shalinib-ibm/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
21 workflow run results
21 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Exp: Perf Benefit with xvi8ger4pp signed version CI #21: Pull request #12 opened by shalinib-ibm
56m 58s xvi8ger4pp_signed_signed
xvi8ger4pp_signed_signed
56m 58s
Move packing from inside MMA kernels CI #20: Pull request #11 opened by shalinib-ibm
56m 59s ppc_f32_move_pack
ppc_f32_move_pack
56m 59s
Refactor: Move matrix packing outside GEMM kernels CI #19: Pull request #10 opened by shalinib-ibm
58m 35s prepack_tinyblas_ppc
prepack_tinyblas_ppc
58m 35s
Avoid PackTranspose calls Fp32 tiny blas kernels CI #18: Pull request #9 opened by shalinib-ibm
56m 4s tinyblas_ppc_opt
tinyblas_ppc_opt
56m 4s
Optimize ggml_vec_dot_q8_q8 for ppc CI #17: Pull request #8 opened by shalinib-ibm
52m 41s splat_rem_vec_dot_q8_q8
splat_rem_vec_dot_q8_q8
52m 41s
Manual unrolling of loop for vec_dot_q8_q8 CI #16: Pull request #7 opened by shalinib-ibm
1h 1m 53s unroll_vec_dot_q8_q8
unroll_vec_dot_q8_q8
1h 1m 53s
ggml_vec_dot_q8_q8 mma optimize CI #15: Pull request #6 opened by shalinib-ibm
1h 2m 33s vec_dot_q8_q8
vec_dot_q8_q8
1h 2m 33s
kv-cache : add SWA support (#13194) CI #14: Commit e298d2f pushed by shalinib-ibm
1h 1m 42s master
master
1h 1m 42s
minja: sync (qwen3) (#13573) CI #13: Commit bc098c3 pushed by shalinib-ibm
1h 2m 4s master
master
1h 2m 4s
mtmd : add qwen2vl and qwen2.5vl (#13141) CI #12: Commit 00e3e5a pushed by shalinib-ibm
43m 43s master
master
43m 43s
llama-graph : fix text position for mrope (#13159) CI #11: Commit b6ce743 pushed by shalinib-ibm
56m 4s master
master
56m 4s
Bug fix CI #10: Pull request #5 opened by shalinib-ibm
46m 9s bug_fix
bug_fix
46m 9s
llama-chat : fix typo GML --> GLM (#13143) CI #9: Commit e5d6c25 pushed by shalinib-ibm
1h 6m 49s master
master
1h 6m 49s
PowerPC: Enable MMA for BF16 in llamafile_sgemm CI #8: Pull request #4 opened by shalinib-ibm
47m 17s bf16_ppc
bf16_ppc
47m 17s
PowerPC: Enable MMA for BF16 in llamafile_sgemm CI #7: Pull request #3 opened by shalinib-ibm
42m 36s tmp_br
tmp_br
42m 36s
PowerPC: Enable MMA for BF16 in llamafile_sgemm CI #6: Pull request #2 synchronize by shalinib-ibm
40m 17s bf16_sgemm
bf16_sgemm
40m 17s
PowerPC: Enable MMA for BF16 in llamafile_sgemm CI #5: Pull request #2 synchronize by shalinib-ibm
48m 43s bf16_sgemm
bf16_sgemm
48m 43s
PowerPC: Enable MMA for BF16 in llamafile_sgemm CI #4: Pull request #2 opened by shalinib-ibm
9m 55s bf16_sgemm
bf16_sgemm
9m 55s
arg : fix unused variable (#13142) CI #3: Commit 85f36e5 pushed by shalinib-ibm
43m 51s master
master
43m 51s
llama-bench : Add --override-tensors arg (#12922) CI #2: Commit c0a97b7 pushed by shalinib-ibm
49m 13s master
master
49m 13s
llama-mtmd-cli: Sigint rework in mtmd vision example (#13080) CI #1: Commit 5630406 pushed by shalinib-ibm
53m 47s master
master
53m 47s