Skip to content

Actions: Tencent/ncnn

Actions

linux-x64-gpu-gcc

Actions

Loading...
Loading

Showing runs from all workflows named linux-x64-gpu-gcc
1,718 workflow run results
1,718 workflow run results

Filter by Workflow

⌥ + click/return to exclude

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
vulkan: fix fp16 arithmetic types in erf and celu shaders linux-x64-gpu-gcc #9339: Pull request #6927 opened by futz12
Action required futz12:fix/erf-celu-fp16-arithmetic
futz12:fix/erf-celu-fp16-arithmetic
Action required
let float2bfloat round to nearest, even or ties away from zero linux-x64-gpu-gcc #9338: Pull request #6925 synchronize by nihui
1h 7m 34s nihui:bf16-rne
nihui:bf16-rne
1h 7m 34s
let float2bfloat round to nearest, even or ties away from zero linux-x64-gpu-gcc #9337: Pull request #6925 opened by nihui
7m 15s nihui:bf16-rne
nihui:bf16-rne
7m 15s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9336: Pull request #6923 synchronize by nihui
1h 1m 14s nihui:sdpa-fa2
nihui:sdpa-fa2
1h 1m 14s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9335: Pull request #6923 synchronize by nihui
13m 43s nihui:sdpa-fa2
nihui:sdpa-fa2
13m 43s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9334: Pull request #6923 synchronize by nihui
41m 15s nihui:sdpa-fa2
nihui:sdpa-fa2
41m 15s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9333: Pull request #6923 synchronize by nihui
13s nihui:sdpa-fa2
nihui:sdpa-fa2
13s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9332: Pull request #6923 synchronize by nihui
4m 17s nihui:sdpa-fa2
nihui:sdpa-fa2
4m 17s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9331: Pull request #6923 synchronize by nihui
51m 41s nihui:sdpa-fa2
nihui:sdpa-fa2
51m 41s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9330: Pull request #6923 synchronize by nihui
1h 4m 32s nihui:sdpa-fa2
nihui:sdpa-fa2
1h 4m 32s
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9329: Pull request #6923 synchronize by github-actions Bot
Action required nihui:sdpa-fa2
nihui:sdpa-fa2
Action required
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9328: Pull request #6923 synchronize by nihui
36m 45s nihui:sdpa-fa2
nihui:sdpa-fa2
36m 45s
fix: stabilize logaddexp expression evaluation linux-x64-gpu-gcc #9327: Pull request #6924 opened by primorLee
Action required primorLee:codex/fix-expression-logaddexp-overflow
primorLee:codex/fix-expression-logaddexp-overflow
Action required
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9326: Pull request #6923 synchronize by nihui
1h 0m 26s nihui:sdpa-fa2
nihui:sdpa-fa2
1h 0m 26s
vulkan 1D convolution family: conv1d winograd/subgroup, convolutiondepthwise1d, deconvolution1d linux-x64-gpu-gcc #9325: Pull request #6909 synchronize by futz12
Action required futz12:1d-conv-vulkan
futz12:1d-conv-vulkan
Action required
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9324: Pull request #6923 synchronize by github-actions Bot
Action required nihui:sdpa-fa2
nihui:sdpa-fa2
Action required
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float linux-x64-gpu-gcc #9323: Pull request #6923 opened by nihui
59m 41s nihui:sdpa-fa2
nihui:sdpa-fa2
59m 41s
fix unvalidated layer counts, out-of-bounds blob index and division by zero in load_param and load_param_bin linux-x64-gpu-gcc #9322: Pull request #6922 synchronize by kaltsit-10
Action required kaltsit-10:fix/text-layer-count
kaltsit-10:fix/text-layer-count
Action required
fix unvalidated layer counts, out-of-bounds blob index and division by zero in load_param and load_param_bin linux-x64-gpu-gcc #9321: Pull request #6922 synchronize by kaltsit-10
Action required kaltsit-10:fix/text-layer-count
kaltsit-10:fix/text-layer-count
Action required
fix unvalidated layer counts, out-of-bounds blob index and division by zero in load_param and load_param_bin linux-x64-gpu-gcc #9320: Pull request #6922 opened by kaltsit-10
Action required kaltsit-10:fix/text-layer-count
kaltsit-10:fix/text-layer-count
Action required
initialize softmax layer pointer in YoloDetectionOutput linux-x64-gpu-gcc #9319: Pull request #6921 opened by kaltsit-10
Action required kaltsit-10:fix/ydo-softmax-init
kaltsit-10:fix/ydo-softmax-init
Action required
x86/loongarch/mips: refine rsqrt with newton-raphson iterations && vu… linux-x64-gpu-gcc #9316: Commit 946fe3f pushed by nihui
1h 56m 48s master
master
1h 56m 48s
x86/loongarch/mips: refine rsqrt with newton-raphson iterations && vulkan: use fp32 for coefficient linux-x64-gpu-gcc #9315: Pull request #6903 synchronize by nihui
1h 5m 56s futz12:rsqrt-precise-fix
futz12:rsqrt-precise-fix
1h 5m 56s
x86/loongarch/mips: refine rsqrt with newton-raphson iterations && vulkan: use fp32 for coefficient linux-x64-gpu-gcc #9314: Pull request #6903 synchronize by futz12
1h 2m 12s futz12:rsqrt-precise-fix
futz12:rsqrt-precise-fix
1h 2m 12s
x86/loongarch/mips: refine rsqrt with newton-raphson iterations && vulkan: use fp32 for coefficient linux-x64-gpu-gcc #9311: Pull request #6903 synchronize by futz12
19m 3s futz12:rsqrt-precise-fix
futz12:rsqrt-precise-fix
19m 3s