Skip to content

Actions: ggml-org/llama.cpp

Actions

Build on RISCV Linux Machine by Cloud-V

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-riscv-native.yml
2,045 workflow run results
2,045 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal : avoid using Metal's gpuAddress property Build on RISCV Linux Machine by Cloud-V #2379: Pull request #16576 synchronize by ggerganov
9m 20s gg/metal-avoid-gpu-address
gg/metal-avoid-gpu-address
9m 20s
metal : avoid using Metal's gpuAddress property Build on RISCV Linux Machine by Cloud-V #2378: Pull request #16576 opened by ggerganov
24m 44s gg/metal-avoid-gpu-address
gg/metal-avoid-gpu-address
24m 44s
ggml-cpu: build fails with -Werror=discarded-qualifiers Build on RISCV Linux Machine by Cloud-V #2376: Pull request #16573 synchronize by otegami
10m 19s otegami:fix/ggml-cpu-setenv-const-correctness
otegami:fix/ggml-cpu-setenv-const-correctness
10m 19s
CUDA: add fp kernel for larger batch size MoE Build on RISCV Linux Machine by Cloud-V #2375: Pull request #16512 synchronize by am17an
10m 14s am17an:cuda_mmf_mmid_opt
am17an:cuda_mmf_mmid_opt
10m 14s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Build on RISCV Linux Machine by Cloud-V #2374: Pull request #16557 synchronize by am17an
10m 11s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
10m 11s
ggml-cpu: build fails with -Werror=discarded-qualifiers Build on RISCV Linux Machine by Cloud-V #2372: Pull request #16573 opened by otegami
18m 33s otegami:fix/ggml-cpu-setenv-const-correctness
otegami:fix/ggml-cpu-setenv-const-correctness
18m 33s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Build on RISCV Linux Machine by Cloud-V #2371: Pull request #16557 synchronize by am17an
10m 15s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
10m 15s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Build on RISCV Linux Machine by Cloud-V #2368: Pull request #16557 synchronize by am17an
6m 0s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
6m 0s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Build on RISCV Linux Machine by Cloud-V #2367: Pull request #16557 synchronize by am17an
11m 40s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
11m 40s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Build on RISCV Linux Machine by Cloud-V #2366: Pull request #16557 synchronize by am17an
5m 58s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
5m 58s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Build on RISCV Linux Machine by Cloud-V #2365: Pull request #16557 synchronize by am17an
6m 4s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
6m 4s
CUDA: add fp kernel for larger batch size MoE Build on RISCV Linux Machine by Cloud-V #2364: Pull request #16512 synchronize by am17an
6m 1s am17an:cuda_mmf_mmid_opt
am17an:cuda_mmf_mmid_opt
6m 1s
CUDA: add fp kernel for larger batch size MoE Build on RISCV Linux Machine by Cloud-V #2363: Pull request #16512 synchronize by am17an
6m 4s am17an:cuda_mmf_mmid_opt
am17an:cuda_mmf_mmid_opt
6m 4s
CUDA: use fastdiv + ggml_cuda_mad for mmvf Build on RISCV Linux Machine by Cloud-V #2362: Pull request #16557 synchronize by am17an
6m 3s am17an:cuda_mmvf_fastdiv
am17an:cuda_mmvf_fastdiv
6m 3s
CANN: Format ggml-cann src code using clang-format Build on RISCV Linux Machine by Cloud-V #2361: Pull request #15863 synchronize by noemotiovon
6m 21s noemotiovon:format
noemotiovon:format
6m 21s
Add experimental ggml-hexagon backend for the Hexagon NPU Build on RISCV Linux Machine by Cloud-V #2354: Pull request #16547 synchronize by max-krasnyansky
10m 33s CodeLinaro:hexagon
CodeLinaro:hexagon
10m 33s
graph : reuse SSM graphs Build on RISCV Linux Machine by Cloud-V #2352: Pull request #16490 synchronize by ggerganov
10m 36s gg/graph-mamba-reuse
gg/graph-mamba-reuse
10m 36s
metal : FA support F32 K and V Build on RISCV Linux Machine by Cloud-V #2351: Pull request #16531 synchronize by ggerganov
9m 48s gg/metal-fa-f32-inp
gg/metal-fa-f32-inp
9m 48s
server : dynamic token limit for prompt cache Build on RISCV Linux Machine by Cloud-V #2350: Pull request #16560 synchronize by ggerganov
10m 18s gg/server-dynamic-token-limit-for-prompt-cache
gg/server-dynamic-token-limit-for-prompt-cache
10m 18s
graph : support cacheless embeddings with FA and iSWA Build on RISCV Linux Machine by Cloud-V #2349: Pull request #16528 synchronize by ggerganov
10m 17s gg/cacheless-embd
gg/cacheless-embd
10m 17s
embedding: add raw option for --embd-output-format Build on RISCV Linux Machine by Cloud-V #2347: Pull request #16541 synchronize by SamMalayek
6m 12s SamMalayek:feature/raw-embedding-output
SamMalayek:feature/raw-embedding-output
6m 12s
Leverage the existing GGML_F32_VEC helpers to vectorize ggml_vec_set_f32 for faster fills Build on RISCV Linux Machine by Cloud-V #2344: Pull request #16522 synchronize by sirus20x6
7m 17s sirus20x6:vectorize-vec-set-f32
sirus20x6:vectorize-vec-set-f32
7m 17s
vulkan: Add ACC_TYPE_VEC2 implementation Build on RISCV Linux Machine by Cloud-V #2343: Pull request #16203 synchronize by SavicStefan
10m 20s SavicStefan:acc_type_vec2
SavicStefan:acc_type_vec2
10m 20s
graph : support cacheless embeddings with FA and iSWA Build on RISCV Linux Machine by Cloud-V #2342: Pull request #16528 synchronize by ggerganov
11m 50s gg/cacheless-embd
gg/cacheless-embd
11m 50s
CUDA: fix numerical issue in tile FA kernel Build on RISCV Linux Machine by Cloud-V #2340: Pull request #16540 synchronize by JohannesGaessler
32m 45s JohannesGaessler:cuda-fa-fix-numerics
JohannesGaessler:cuda-fa-fix-numerics
32m 45s