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
2,789 workflow run results
2,789 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Build on RISCV Linux Machine by Cloud-V #3003: Pull request #16574 synchronize by pockers21
25m 50s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
25m 50s
ggml-hexagon: respect input size when getting/setting tensor data Build on RISCV Linux Machine by Cloud-V #3001: Pull request #16836 opened by l3utterfly
6m 37s l3utterfly:patch-1
l3utterfly:patch-1
6m 37s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Build on RISCV Linux Machine by Cloud-V #3002: Pull request #16574 synchronize by pockers21
19m 43s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
19m 43s
hip: add RDNA4 support for mmf and mma Build on RISCV Linux Machine by Cloud-V #3000: Pull request #16835 opened by zhang-hui-yulo
19m 9s zhang-hui-yulo:mmf_for_rdna4
zhang-hui-yulo:mmf_for_rdna4
19m 9s
CUDA: use fastdiv in set-rows Build on RISCV Linux Machine by Cloud-V #2999: Pull request #16834 opened by am17an
6m 38s am17an:cuda-fast-div-setrows
am17an:cuda-fast-div-setrows
6m 38s
[model] add support for qwen3vl series Build on RISCV Linux Machine by Cloud-V #2998: Pull request #16780 synchronize by JJJYmmm
26m 30s JJJYmmm:add_qwen3vl
JJJYmmm:add_qwen3vl
26m 30s
CUDA: Fix bug in topk-moe for gpt-oss Build on RISCV Linux Machine by Cloud-V #2997: Pull request #16821 synchronize by am17an
6m 44s am17an:fix_topk_cuda
am17an:fix_topk_cuda
6m 44s
vulkan: Fix crash when FP16 mul_mat accumulation is not supported Build on RISCV Linux Machine by Cloud-V #2996: Pull request #16796 synchronize by rillomas
7m 26s rillomas:fix-accf16-capability-crash
rillomas:fix-accf16-capability-crash
7m 26s
cpu: introduce chunking for repack matmuls and enable matmul-id chunking Build on RISCV Linux Machine by Cloud-V #2995: Pull request #16833 opened by max-krasnyansky
7m 17s qualcomm:repack-matmul-chunking
qualcomm:repack-matmul-chunking
7m 17s
vulkan: Fix crash when FP16 mul_mat accumulation is not supported Build on RISCV Linux Machine by Cloud-V #2994: Pull request #16796 synchronize by rillomas
6m 37s rillomas:fix-accf16-capability-crash
rillomas:fix-accf16-capability-crash
6m 37s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #2993: Pull request #16831 synchronize by pwilkin
20m 58s pwilkin:minimax-m2
pwilkin:minimax-m2
20m 58s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #2992: Pull request #16831 synchronize by pwilkin
22m 54s pwilkin:minimax-m2
pwilkin:minimax-m2
22m 54s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #2991: Pull request #16831 synchronize by pwilkin
16m 36s pwilkin:minimax-m2
pwilkin:minimax-m2
16m 36s
Model: Minimax M2 Build on RISCV Linux Machine by Cloud-V #2990: Pull request #16831 synchronize by pwilkin
12m 19s pwilkin:minimax-m2
pwilkin:minimax-m2
12m 19s
arm64: add i8mm route with SVE ggml_vec_dot_q4_K_q8_K and ggml_vec_dot_q6_K_… Build on RISCV Linux Machine by Cloud-V #2989: Pull request #15277 synchronize by fj-y-saito
6m 36s fj-y-saito:feat-sve-i8mm-q4_K_quantization
fj-y-saito:feat-sve-i8mm-q4_K_quantization
6m 36s
cpu: introduce chunking for flash attention Build on RISCV Linux Machine by Cloud-V #2988: Pull request #16829 opened by max-krasnyansky
7m 59s qualcomm:flashattn-chunking
qualcomm:flashattn-chunking
7m 59s
llama: store mrope data in KV cell Build on RISCV Linux Machine by Cloud-V #2987: Pull request #16825 synchronize by ngxson
11m 4s ngxson:xsn/fix-mrope-causal
ngxson:xsn/fix-mrope-causal
11m 4s
CUDA: Conv2d tensor core Build on RISCV Linux Machine by Cloud-V #2986: Pull request #16828 opened by mnehete32
6m 48s mnehete32:conv2d_tensor_core
mnehete32:conv2d_tensor_core
6m 48s
vulkan: remove the need for the dryrun Build on RISCV Linux Machine by Cloud-V #2984: Pull request #16826 opened by jeffbolznv
6m 42s jeffbolznv:dryrun
jeffbolznv:dryrun
6m 42s
server : remove n_past Build on RISCV Linux Machine by Cloud-V #2983: Pull request #16818 synchronize by ggerganov
13m 1s gg/server-fix-n-past
gg/server-fix-n-past
13m 1s
llama: store mrope data in KV cell Build on RISCV Linux Machine by Cloud-V #2982: Pull request #16825 opened by ngxson
12m 6s ngxson:xsn/fix-mrope-causal
ngxson:xsn/fix-mrope-causal
12m 6s
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization Build on RISCV Linux Machine by Cloud-V #2981: Pull request #16653 synchronize by JohannesGaessler
25m 17s JohannesGaessler:llama-memory-fit-9
JohannesGaessler:llama-memory-fit-9
25m 17s
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
ProTip! You can narrow down the results and go further in time using created:<2025-10-28 or the other filters available.