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
2,612 workflow run results
2,612 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Refactor llama-model.cpp Build on RISCV Linux Machine by Cloud-V #2980: Pull request #16252 synchronize by pwilkin
11m 4s pwilkin:llama-cpp-refactor
pwilkin:llama-cpp-refactor
11m 4s
llama-bench : clarify benchmarked parts of the computation Build on RISCV Linux Machine by Cloud-V #2979: Pull request #16823 opened by ggerganov
11m 26s gg/bench-clarify
gg/bench-clarify
11m 26s
CUDA: Fix bug in topk-moe for gpt-oss Build on RISCV Linux Machine by Cloud-V #2978: Pull request #16821 synchronize by am17an
6m 45s am17an:fix_topk_cuda
am17an:fix_topk_cuda
6m 45s
llama: add linearly increasing token dim for M-RoPE Build on RISCV Linux Machine by Cloud-V #2977: Pull request #16822 opened by ngxson
29m 1s ngxson:xsn/fix-mrope
ngxson:xsn/fix-mrope
29m 1s
Hexagon Op queue & dispatch optimizations Build on RISCV Linux Machine by Cloud-V #2976: Pull request #16820 synchronize by max-krasnyansky
58m 31s qualcomm:hexagon-dspqueue-opts
qualcomm:hexagon-dspqueue-opts
58m 31s
CUDA: Fix bug in topk-moe for gpt-oss Build on RISCV Linux Machine by Cloud-V #2975: Pull request #16821 opened by am17an
31m 20s am17an:fix_topk_cuda
am17an:fix_topk_cuda
31m 20s
Hexagon Op queue & dispatch optimizations Build on RISCV Linux Machine by Cloud-V #2974: Pull request #16820 opened by max-krasnyansky
26m 48s qualcomm:hexagon-dspqueue-opts
qualcomm:hexagon-dspqueue-opts
26m 48s
server/public_simplechat client ui show reasoning support added, toolcalling with direct builtin tools and beyond also in PR chain Build on RISCV Linux Machine by Cloud-V #2973: Pull request #16819 opened by hanishkvc
22m 27s hanishkvc:hkvc_server_simplechat_toolcalling_v0420
hanishkvc:hkvc_server_simplechat_toolcalling_v0420
22m 27s
Vulkan MMQ Integer Dot Refactor and K-Quant support Build on RISCV Linux Machine by Cloud-V #2972: Pull request #16536 synchronize by 0cc4m
3m 3s 0cc4m/vulkan-mmq-dp4a-k-quants
0cc4m/vulkan-mmq-dp4a-k-quants
3m 3s
ggml-cpu: arm64: q4_K repack gemm and gemv implementations (i8mm) Build on RISCV Linux Machine by Cloud-V #2971: Pull request #16739 synchronize by Alcpz
3m 21s Alcpz:Alcpz/arm_q4_k_repack
Alcpz:Alcpz/arm_q4_k_repack
3m 21s
server : remove n_past Build on RISCV Linux Machine by Cloud-V #2970: Pull request #16818 opened by ggerganov
47m 23s gg/server-fix-n-past
gg/server-fix-n-past
47m 23s
cuda : Add conv2d Implicit GEMM Build on RISCV Linux Machine by Cloud-V #2968: Pull request #15805 synchronize by bssrdf
1h 21m 51s bssrdf:conv2d-implicit
bssrdf:conv2d-implicit
1h 21m 51s
cuda : Add conv2d Implicit GEMM Build on RISCV Linux Machine by Cloud-V #2967: Pull request #15805 reopened by bssrdf
1h 15m 27s bssrdf:conv2d-implicit
bssrdf:conv2d-implicit
1h 15m 27s
ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 Build on RISCV Linux Machine by Cloud-V #2966: Pull request #16805 synchronize by duduta
49m 24s duduta:refactor-rope
duduta:refactor-rope
49m 24s
llama-cli: add support for reasoning Build on RISCV Linux Machine by Cloud-V #2965: Pull request #16603 synchronize by bandoti
48m 11s bandoti:llamacli-reasoning2
bandoti:llamacli-reasoning2
48m 11s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Build on RISCV Linux Machine by Cloud-V #2964: Pull request #16817 opened by yael-works
32m 11s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
32m 11s
[bug fix] initialise buffer.device in ggml_hexagon_session Build on RISCV Linux Machine by Cloud-V #2963: Pull request #16816 opened by l3utterfly
6m 39s l3utterfly:patch-2
l3utterfly:patch-2
6m 39s
metal : initial Metal4 tensor API support Build on RISCV Linux Machine by Cloud-V #2961: Pull request #16634 synchronize by ggerganov
6m 41s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
6m 41s
server : support unified cache across slots Build on RISCV Linux Machine by Cloud-V #2960: Pull request #16736 synchronize by ggerganov
50m 23s gg/server-unified-slots
gg/server-unified-slots
50m 23s
memory : remove KV cache size padding Build on RISCV Linux Machine by Cloud-V #2959: Pull request #16812 synchronize by ggerganov
44m 17s gg/context-no-pad
gg/context-no-pad
44m 17s
Vulkan MMQ Integer Dot Refactor and K-Quant support Build on RISCV Linux Machine by Cloud-V #2958: Pull request #16536 synchronize by 0cc4m
32m 27s 0cc4m/vulkan-mmq-dp4a-k-quants
0cc4m/vulkan-mmq-dp4a-k-quants
32m 27s
llama: Fused QKV multiplication Build on RISCV Linux Machine by Cloud-V #2955: Pull request #16813 synchronize by am17an
43m 54s am17an:fused-qkv
am17an:fused-qkv
43m 54s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Build on RISCV Linux Machine by Cloud-V #2954: Pull request #16574 synchronize by pockers21
39m 17s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
39m 17s
sycl: add RMS_NORM_BACK operation support Build on RISCV Linux Machine by Cloud-V #2953: Pull request #16808 synchronize by YaelLogic
38m 34s YaelLogic:rms_norm_back_sycl
YaelLogic:rms_norm_back_sycl
38m 34s
server : support unified cache across slots Build on RISCV Linux Machine by Cloud-V #2952: Pull request #16736 synchronize by ggerganov
45m 54s gg/server-unified-slots
gg/server-unified-slots
45m 54s