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
2,917 workflow run results
2,917 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

add TheRock HIP backend build instructions Build on RISCV Linux Machine by Cloud-V #3281: Pull request #16915 synchronize by lihaofd
Action required lihaofd:master
lihaofd:master
Action required
add TheRock HIP backend build instructions Build on RISCV Linux Machine by Cloud-V #3280: Pull request #16915 synchronize by lihaofd
Action required lihaofd:master
lihaofd:master
Action required
improve CUDA cpy memory bandwidth when copying transposed tensor Build on RISCV Linux Machine by Cloud-V #3279: Pull request #16841 synchronize by bssrdf
28m 51s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
28m 51s
server/public_simplechat - with reasoning and 0 setup builtin tool calls data store, calculator, javascript code runner, with simpleproxy helper web fetch, web search, pdf2text tool calls Build on RISCV Linux Machine by Cloud-V #3278: Pull request #16929 synchronize by hanishkvc
24m 0s hanishkvc:hkvc_server_simplechat_toolcalling_v0440
hanishkvc:hkvc_server_simplechat_toolcalling_v0440
24m 0s
Fix segfault in moe-expert-reduce test in support mode and coverage Build on RISCV Linux Machine by Cloud-V #3277: Pull request #16936 opened by sbera77
21m 4s sbera77:master
sbera77:master
21m 4s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Build on RISCV Linux Machine by Cloud-V #3276: Pull request #16817 synchronize by yael-works
32m 33s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
32m 33s
CUDA: avoid mul + bias fusion when buffers are split Build on RISCV Linux Machine by Cloud-V #3275: Pull request #16935 opened by am17an
13m 18s am17an:cuda-fix-sm-row
am17an:cuda-fix-sm-row
13m 18s
clip : use FA Build on RISCV Linux Machine by Cloud-V #3274: Pull request #16837 synchronize by ngxson
26m 49s gg/clip-fa
gg/clip-fa
26m 49s
clip : use FA Build on RISCV Linux Machine by Cloud-V #3273: Pull request #16837 synchronize by ngxson
23m 25s gg/clip-fa
gg/clip-fa
23m 25s
Vulkan: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Build on RISCV Linux Machine by Cloud-V #3272: Pull request #16686 synchronize by safranowith
3m 4s safranowith:add-operators-valkan
safranowith:add-operators-valkan
3m 4s
Vulkan: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Build on RISCV Linux Machine by Cloud-V #3271: Pull request #16686 synchronize by safranowith
3m 4s safranowith:add-operators-valkan
safranowith:add-operators-valkan
3m 4s
Vulkan: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Build on RISCV Linux Machine by Cloud-V #3270: Pull request #16686 synchronize by safranowith
3m 3s safranowith:add-operators-valkan
safranowith:add-operators-valkan
3m 3s
Vulkan: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators Build on RISCV Linux Machine by Cloud-V #3268: Pull request #16686 synchronize by safranowith
3m 6s safranowith:add-operators-valkan
safranowith:add-operators-valkan
3m 6s
server : support unified cache across slots Build on RISCV Linux Machine by Cloud-V #3267: Pull request #16736 synchronize by ggerganov
7m 50s gg/server-unified-slots
gg/server-unified-slots
7m 50s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Build on RISCV Linux Machine by Cloud-V #3264: Pull request #16817 synchronize by yael-works
-2093s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
-2093s
server: add minimax-m2 reasoning format override for MiniMax-M2 compatibility Build on RISCV Linux Machine by Cloud-V #3266: Pull request #16933 opened by ServeurpersoCom
29m 2s ServeurpersoCom:reasoning-format-minimax-m2
ServeurpersoCom:reasoning-format-minimax-m2
29m 2s
benches : add folder with benchmarks Build on RISCV Linux Machine by Cloud-V #3263: Pull request #16931 opened by ggerganov
6m 37s gg/benches
gg/benches
6m 37s
clip : use FA Build on RISCV Linux Machine by Cloud-V #3262: Pull request #16837 synchronize by ggerganov
15m 48s gg/clip-fa
gg/clip-fa
15m 48s
ggml webgpu: minor set rows optimization Build on RISCV Linux Machine by Cloud-V #3261: Pull request #16810 synchronize by reeselevine
6m 44s reeselevine:master
reeselevine:master
6m 44s
server/public_simplechat - with reasoning and 0 setup builtin tool calls data store, calculator, javascript code runner, with simpleproxy helper web fetch, web search, pdf2text tool calls Build on RISCV Linux Machine by Cloud-V #3260: Pull request #16929 opened by hanishkvc
3m 24s hanishkvc:hkvc_server_simplechat_toolcalling_v0440
hanishkvc:hkvc_server_simplechat_toolcalling_v0440
3m 24s
clip : use FA Build on RISCV Linux Machine by Cloud-V #3259: Pull request #16837 synchronize by ngxson
14m 37s gg/clip-fa
gg/clip-fa
14m 37s
hparams : add n_embd_inp() to support extended embed Build on RISCV Linux Machine by Cloud-V #3258: Pull request #16928 opened by CISC
29m 26s cisc/support-extended-embd
cisc/support-extended-embd
29m 26s
Add initial devcontainer configuration Build on RISCV Linux Machine by Cloud-V #3257: Pull request #16926 opened by FXJEFE
Action required FXJEFE:patch-2
FXJEFE:patch-2
Action required
Attempt to remove embd mangling for Qwen3VL and Qwen3VL-MOE Build on RISCV Linux Machine by Cloud-V #3256: Pull request #16925 opened by 65a
9m 59s 65a:master
65a:master
9m 59s
cuda: allow ggml_cuda_cpy to copy contiguous F32 and F16 tensors greater than INT_MAX Build on RISCV Linux Machine by Cloud-V #3255: Pull request #16924 opened by jukofyork
6m 42s jukofyork:cuda-cpy-assert-fix
jukofyork:cuda-cpy-assert-fix
6m 42s