Skip to content

Actions: AMD-Ecosystem/llama.cpp

Actions

Code Style Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
code-style.yml
194 workflow runs
194 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: GEMM weight row padding + one-time K-padded f16 dequant for prefill Code Style Checker #96: Pull request #57 opened by roberteg16
32s rogarcia.cuda-gemm-pad-prefill-dequant
rogarcia.cuda-gemm-pad-prefill-dequant
32s
ggml-cuda: enable GGML_CUDA_GRAPH_OPT by default on RDNA3.5 Code Style Checker #95: Pull request #56 opened by roberteg16
46s rogarcia.enable-by-default-ggml_cuda_graph_opt-on
rogarcia.enable-by-default-ggml_cuda_graph_opt-on
46s
Merge pull request #53 from ROCm/rogarcia.roofline-moe-tokens-per-expert Code Style Checker #94: Commit 0941c4c pushed by mgehre-amd
42s gfx11
gfx11
42s
CUDA: fused chunked gated_delta_net kernel (RDNA3.5) Code Style Checker #91: Pull request #54 synchronize by roberteg16
22s rogarcia.gdn-shared-kq
rogarcia.gdn-shared-kq
22s
CUDA: fused chunked gated_delta_net kernel (RDNA3.5) Code Style Checker #90: Pull request #54 opened by roberteg16
29s rogarcia.gdn-shared-kq
rogarcia.gdn-shared-kq
29s
roofline: emit per-expert routing histogram (tokens_per_expert) for MoE launches Code Style Checker #89: Pull request #53 opened by roberteg16
1m 12s rogarcia.roofline-moe-tokens-per-expert
rogarcia.roofline-moe-tokens-per-expert
1m 12s
Merge pull request #52 from ROCm/rogarcia.qwen3.6-moe-optimization Code Style Checker #88: Commit f6ea7bc pushed by roberteg16
20s gfx11
gfx11
20s
ssm_conv: channels-major input mode to drop the delta-net transpose Code Style Checker #87: Pull request #52 synchronize by roberteg16
1m 22s rogarcia.qwen3.6-moe-optimization
rogarcia.qwen3.6-moe-optimization
1m 22s
Merge pull request #36 from ROCm/rogarcia.cuda-multistream-shexp Code Style Checker #86: Commit 367c4d0 pushed by roberteg16
17s gfx11
gfx11
17s
ssm_conv: channels-major input mode to drop the delta-net transpose Code Style Checker #85: Pull request #52 synchronize by roberteg16
53s rogarcia.qwen3.6-moe-optimization
rogarcia.qwen3.6-moe-optimization
53s
ggml-cuda: overlap the MoE shared expert on a separate stream Code Style Checker #84: Pull request #36 synchronize by roberteg16
23s rogarcia.cuda-multistream-shexp
rogarcia.cuda-multistream-shexp
23s
Merge pull request #50 from ROCm/rogarcia.roofline-moe-experts-used Code Style Checker #83: Commit 442b17e pushed by roberteg16
1m 5s gfx11
gfx11
1m 5s
ssm_conv: channels-major input mode to drop the delta-net transpose Code Style Checker #82: Pull request #52 synchronize by roberteg16
25s rogarcia.qwen3.6-moe-optimization
rogarcia.qwen3.6-moe-optimization
25s
ssm_conv: channels-major input mode to drop the delta-net transpose Code Style Checker #81: Pull request #52 synchronize by roberteg16
19s rogarcia.qwen3.6-moe-optimization
rogarcia.qwen3.6-moe-optimization
19s
roofline: capture per-launch MoE active-expert count (experts_used) Code Style Checker #80: Pull request #50 synchronize by roberteg16
1m 6s rogarcia.roofline-moe-experts-used
rogarcia.roofline-moe-experts-used
1m 6s
Merge pull request #48 from ROCm/rogarcia.roofline-fused-raw-facts Code Style Checker #79: Commit ffe2ad4 pushed by mgehre-amd
44s gfx11
gfx11
44s
Merge pull request #51 from ROCm/rogarcia.fix-ci-llamacpp Code Style Checker #78: Commit 77939b0 pushed by mgehre-amd
27s gfx11
gfx11
27s
Merge pull request #49 from ROCm/rogarcia.cuda-mmvf-single-col-swap Code Style Checker #77: Commit a4498c2 pushed by mgehre-amd
44s gfx11
gfx11
44s
ssm_conv: channels-major input mode to drop the delta-net transpose Code Style Checker #76: Pull request #52 synchronize by roberteg16
1m 8s rogarcia.qwen3.6-moe-optimization
rogarcia.qwen3.6-moe-optimization
1m 8s
ssm_conv: channels-major input mode to drop the delta-net transpose Code Style Checker #75: Pull request #52 opened by roberteg16
20s rogarcia.qwen3.6-moe-optimization
rogarcia.qwen3.6-moe-optimization
20s
fix: ci(hip): drop web UI provisioning from hip-quality-check Code Style Checker #74: Pull request #51 opened by roberteg16
36s rogarcia.fix-ci-llamacpp
rogarcia.fix-ci-llamacpp
36s
RDNA3.5 (gfx11 / gfx1151) MMQ prefill optimizations Code Style Checker #73: Pull request #32 synchronize by liangliangchang
1m 15s liangliangchang:lichang.mmq_opt
liangliangchang:lichang.mmq_opt
1m 15s
roofline: emit raw per-tensor data for DDR byte accounting (single + fused) Code Style Checker #72: Pull request #48 synchronize by roberteg16
53s rogarcia.roofline-fused-raw-facts
rogarcia.roofline-fused-raw-facts
53s
CUDA: route single-column f32 mul_mat through mmvf (transpose-free operand swap) Code Style Checker #71: Pull request #49 synchronize by roberteg16
30s rogarcia.cuda-mmvf-single-col-swap
rogarcia.cuda-mmvf-single-col-swap
30s
CUDA: route single-column f32 mul_mat through mmvf (transpose-free operand swap) Code Style Checker #70: Pull request #49 opened by roberteg16
50s rogarcia.cuda-mmvf-single-col-swap
rogarcia.cuda-mmvf-single-col-swap
50s