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
410 workflow run results
410 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix(ggml-sycl): add synchronization before exiting argsort kernel Build on RISCV Linux Machine by Cloud-V #286: Pull request #15582 synchronize by MengAiDev
4m 49s MengAiDev:15580
MengAiDev:15580
4m 49s
Possible fix: use ne0..ne3 (dst dims) instead of ne00..ne03 in ggml_compute_forward_dup_f16 Build on RISCV Linux Machine by Cloud-V #285: Pull request #15626 opened by kperreau
5m 39s kperreau:fix/ggml-cpu-dup-f16-carry-dst-dims
kperreau:fix/ggml-cpu-dup-f16-carry-dst-dims
5m 39s
ggml : fix SSM_SCAN for n_groups > 1 Build on RISCV Linux Machine by Cloud-V #282: Pull request #15625 opened by compilade
5m 34s compilade/fix-ssm-scan-groups
compilade/fix-ssm-scan-groups
5m 34s
model : add grok-2 support Build on RISCV Linux Machine by Cloud-V #279: Pull request #15539 synchronize by CISC
8m 7s cisc/grok-2
cisc/grok-2
8m 7s
model : add grok-2 support Build on RISCV Linux Machine by Cloud-V #278: Pull request #15539 synchronize by CISC
4m 34s cisc/grok-2
cisc/grok-2
4m 34s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #277: Pull request #14839 synchronize by allozaur
20m 46s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
20m 46s
model : add grok-2 support Build on RISCV Linux Machine by Cloud-V #276: Pull request #15539 synchronize by CISC
21m 44s cisc/grok-2
cisc/grok-2
21m 44s
cuda: Add cublasLt_static linking when GGML_STATIC is enabled Build on RISCV Linux Machine by Cloud-V #275: Pull request #15622 opened by matiaslin
9m 1s matiaslin:link_with_cublasLt_static
matiaslin:link_with_cublasLt_static
9m 1s
nvidia nemotron nano v2 (nemotronh) Build on RISCV Linux Machine by Cloud-V #274: Pull request #15507 synchronize by gabe-l-hart
14m 10s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
14m 10s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #273: Pull request #14839 synchronize by allozaur
29m 19s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
29m 19s
server: higher timeout for tests Build on RISCV Linux Machine by Cloud-V #272: Pull request #15621 opened by JohannesGaessler
40m 17s JohannesGaessler:server-test-timeout
JohannesGaessler:server-test-timeout
40m 17s
llama: use FA + max. GPU layers by default Build on RISCV Linux Machine by Cloud-V #271: Pull request #15434 synchronize by JohannesGaessler
29m 13s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
29m 13s
Deepseek V3.1 native tool calling support (OpenAI Style) Build on RISCV Linux Machine by Cloud-V #269: Pull request #15533 synchronize by createthis
20m 56s createthis:deepseek_3_1_thinking_mode
createthis:deepseek_3_1_thinking_mode
20m 56s
ggml : add ggml_mul_mat_id_set_prec and use in llama.cpp Build on RISCV Linux Machine by Cloud-V #268: Pull request #15619 opened by ggerganov
30m 57s gg/mmid-set-prec
gg/mmid-set-prec
30m 57s
llama: use FA + max. GPU layers by default Build on RISCV Linux Machine by Cloud-V #267: Pull request #15434 synchronize by JohannesGaessler
5m 10s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
5m 10s
llama: use FA + max. GPU layers by default Build on RISCV Linux Machine by Cloud-V #265: Pull request #15434 synchronize by JohannesGaessler
4m 37s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
4m 37s
llama: use FA + max. GPU layers by default Build on RISCV Linux Machine by Cloud-V #264: Pull request #15434 synchronize by JohannesGaessler
16m 17s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
16m 17s
llama: use FA + max. GPU layers by default Build on RISCV Linux Machine by Cloud-V #263: Pull request #15434 synchronize by JohannesGaessler
9m 18s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
9m 18s
llama: use FA + max. GPU layers by default Build on RISCV Linux Machine by Cloud-V #261: Pull request #15434 synchronize by JohannesGaessler
12m 28s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
12m 28s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #258: Pull request #14839 synchronize by allozaur
4m 46s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
4m 46s
presets : add qwen3-30B-a3b FIM Build on RISCV Linux Machine by Cloud-V #257: Pull request #15616 opened by ggerganov
7m 38s gg/presets-fim-add-qwen3-30b-a3b
gg/presets-fim-add-qwen3-30b-a3b
7m 38s
SvelteKit-based WebUI Build on RISCV Linux Machine by Cloud-V #256: Pull request #14839 synchronize by allozaur
4m 43s allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
4m 43s
kv-cache : remove LLAMA_SET_ROWS checks Build on RISCV Linux Machine by Cloud-V #255: Pull request #15505 synchronize by ggerganov
8m 30s gg/kv-cache-remove-set-rows-checks
gg/kv-cache-remove-set-rows-checks
8m 30s
HIP: Enable support for ggml_backend_cuda_register_host_buffer Build on RISCV Linux Machine by Cloud-V #254: Pull request #15615 opened by IMbackK
4m 40s IMbackK:master
IMbackK:master
4m 40s
kleidiai: fix GGML_ASSERT(*cur_backend_id != -1) failed Build on RISCV Linux Machine by Cloud-V #253: Pull request #15614 opened by chaxu01
4m 41s chaxu01:feature/get-rows-assert
chaxu01:feature/get-rows-assert
4m 41s