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
2,205 workflow runs
2,205 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CANN: refactor mask handling and improve performance in FA Build on RISCV Linux Machine by Cloud-V #245: Pull request #15561 synchronize by noemotiovon
4m 39s noemotiovon:fa
noemotiovon:fa
4m 39s
model : add grok-2 support Build on RISCV Linux Machine by Cloud-V #242: Pull request #15539 synchronize by CISC
9m 4s cisc/grok-2
cisc/grok-2
9m 4s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Build on RISCV Linux Machine by Cloud-V #240: Pull request #14891 synchronize by EAddario
9m 53s EAddario:imatrix
EAddario:imatrix
9m 53s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Build on RISCV Linux Machine by Cloud-V #239: Pull request #14891 synchronize by EAddario
4m 42s EAddario:imatrix
EAddario:imatrix
4m 42s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error Build on RISCV Linux Machine by Cloud-V #238: Pull request #15550 synchronize by EAddario
5m 26s EAddario:quantize
EAddario:quantize
5m 26s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #237: Pull request #14839 synchronize by allozaur
4m 38s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
4m 38s
tests : fix test-opt with GGML_BACKEND_DL Build on RISCV Linux Machine by Cloud-V #235: Pull request #15599 opened by slaren
4m 38s sl/fix-test-opt-dl
sl/fix-test-opt-dl
4m 38s
nvidia nemotron nano v2 (nemotronh) Build on RISCV Linux Machine by Cloud-V #234: Pull request #15507 synchronize by gabe-l-hart
8m 13s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
8m 13s
nvidia nemotron nano v2 (nemotronh) Build on RISCV Linux Machine by Cloud-V #233: Pull request #15507 synchronize by gabe-l-hart
8m 18s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
8m 18s
nvidia nemotron nano v2 (nemotronh) Build on RISCV Linux Machine by Cloud-V #232: Pull request #15507 synchronize by gabe-l-hart
8m 16s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
8m 16s
nvidia nemotron nano v2 (nemotronh) Build on RISCV Linux Machine by Cloud-V #231: Pull request #15507 synchronize by gabe-l-hart
8m 21s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
8m 21s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #230: Pull request #14839 synchronize by allozaur
4m 41s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
4m 41s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #229: Pull request #14839 synchronize by allozaur
9m 9s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
9m 9s
nvidia nemotron nano v2 (nemotronh) Build on RISCV Linux Machine by Cloud-V #228: Pull request #15507 synchronize by gabe-l-hart
15m 57s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
15m 57s
SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size Build on RISCV Linux Machine by Cloud-V #227: Pull request #15592 opened by qnixsynapse
9m 55s sycl/fix_rms_norm_mul_add
sycl/fix_rms_norm_mul_add
9m 55s
graph : fix assert in memory-less build_attn Build on RISCV Linux Machine by Cloud-V #224: Pull request #15590 opened by ggerganov
4m 52s gg/graph-no-cache-fix-assert
gg/graph-no-cache-fix-assert
4m 52s
model-conversion : add qat-q4 quantization targets Build on RISCV Linux Machine by Cloud-V #223: Pull request #15588 opened by danbev
4m 34s danbev:model-conversion-qat-q4-quantization
danbev:model-conversion-qat-q4-quantization
4m 34s
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required Build on RISCV Linux Machine by Cloud-V #222: Pull request #15248 synchronize by ExtReMLapin
6m 22s ExtReMLapin:fix_qwen_reasoning_tool_calling_required
ExtReMLapin:fix_qwen_reasoning_tool_calling_required
6m 22s
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required Build on RISCV Linux Machine by Cloud-V #221: Pull request #15248 synchronize by ExtReMLapin
6m 32s ExtReMLapin:fix_qwen_reasoning_tool_calling_required
ExtReMLapin:fix_qwen_reasoning_tool_calling_required
6m 32s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #219: Pull request #14839 synchronize by allozaur
9m 29s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
9m 29s
CANN: refactor mask handling and improve performance in FA Build on RISCV Linux Machine by Cloud-V #218: Pull request #15561 synchronize by noemotiovon
12m 7s noemotiovon:fa
noemotiovon:fa
12m 7s
ggml-cpu : add basic RVV support for vector f32 ops Build on RISCV Linux Machine by Cloud-V #217: Pull request #15057 synchronize by xctan
13m 47s xctan:rvv-vec-h
xctan:rvv-vec-h
13m 47s
CUDA: return -1 for nonexistent compiled arch Build on RISCV Linux Machine by Cloud-V #216: Pull request #15587 synchronize by JohannesGaessler
28m 45s JohannesGaessler:cuda-fix-highest-compiled-arch
JohannesGaessler:cuda-fix-highest-compiled-arch
28m 45s
metal : optimize FA vec for large sequences and BS <= 8 Build on RISCV Linux Machine by Cloud-V #215: Pull request #15566 synchronize by ggerganov
34m 27s gg/metal-fa-vec-opt-2
gg/metal-fa-vec-opt-2
34m 27s
CUDA: return -1 for nonexistent compiled arch Build on RISCV Linux Machine by Cloud-V #214: Pull request #15587 opened by JohannesGaessler
29m 19s JohannesGaessler:cuda-fix-highest-compiled-arch
JohannesGaessler:cuda-fix-highest-compiled-arch
29m 19s
ProTip! You can narrow down the results and go further in time using created:<2025-08-26 or the other filters available.