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
3,204 workflow runs
3,204 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add ops needed for new hybrid models: SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM Build on RISCV Linux Machine by Cloud-V #3640: Pull request #17063 synchronize by pwilkin
35m 14s pwilkin:hybrid_ops
pwilkin:hybrid_ops
35m 14s
Add ops needed for new hybrid models: SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM Build on RISCV Linux Machine by Cloud-V #3639: Pull request #17063 synchronize by pwilkin
29m 28s pwilkin:hybrid_ops
pwilkin:hybrid_ops
29m 28s
server/public_simplechat alternate web client ui with 0 setup builtin tool calling++, reasoning - refactored, SysDateTime, rename pdftext Build on RISCV Linux Machine by Cloud-V #3638: Pull request #17038 synchronize by hanishkvc
6m 5s hanishkvc:hkvc_server_simplechat_toolcalling_v0450
hanishkvc:hkvc_server_simplechat_toolcalling_v0450
6m 5s
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support Build on RISCV Linux Machine by Cloud-V #3637: Pull request #16900 synchronize by 0cc4m
7m 25s 0cc4m/vulkan-mmq-dp4a-vec-k-quants
0cc4m/vulkan-mmq-dp4a-vec-k-quants
7m 25s
metal : enable tensor API for A19 Build on RISCV Linux Machine by Cloud-V #3636: Pull request #17087 opened by ggerganov
29m 1s gg/metal-tensor-a19
gg/metal-tensor-a19
29m 1s
bench : cache the llama_context state at computed depth Build on RISCV Linux Machine by Cloud-V #3635: Pull request #16944 synchronize by ggerganov
7m 32s gg/context-skip-compute
gg/context-skip-compute
7m 32s
cmake: add option to build and link BoringSSL Build on RISCV Linux Machine by Cloud-V #3634: Pull request #17062 synchronize by angt
20m 49s angt:cmake-add-option-to-build-and-link-boringssl
angt:cmake-add-option-to-build-and-link-boringssl
20m 49s
CUDA: fix should_use_mmvf for ne11 == 1 Build on RISCV Linux Machine by Cloud-V #3633: Pull request #17085 synchronize by JohannesGaessler
22m 41s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
22m 41s
CUDA: fix should_use_mmvf for ne11 == 1 Build on RISCV Linux Machine by Cloud-V #3632: Pull request #17085 synchronize by JohannesGaessler
19m 51s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
19m 51s
CUDA: fix should_use_mmvf for ne11 == 1 Build on RISCV Linux Machine by Cloud-V #3631: Pull request #17085 synchronize by JohannesGaessler
26m 16s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
26m 16s
kv-cache : pad the cache size to 256 for performance Build on RISCV Linux Machine by Cloud-V #3630: Pull request #17046 synchronize by ggerganov
22m 26s gg/iswa-pad-256
gg/iswa-pad-256
22m 26s
ggml-cpu : inspect -march and -mcpu to found the CPU Build on RISCV Linux Machine by Cloud-V #3629: Pull request #16333 synchronize by angt
10m 53s angt:inspect-march-and-mcpu-to-found-the-cpu
angt:inspect-march-and-mcpu-to-found-the-cpu
10m 53s
CUDA: fix should_use_mmvf for ne11 == 1 Build on RISCV Linux Machine by Cloud-V #3628: Pull request #17085 opened by JohannesGaessler
21m 58s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
21m 58s
ggml-cpu : inspect -march and -mcpu to found the CPU Build on RISCV Linux Machine by Cloud-V #3627: Pull request #16333 synchronize by angt
12m 17s angt:inspect-march-and-mcpu-to-found-the-cpu
angt:inspect-march-and-mcpu-to-found-the-cpu
12m 17s
Revert "ggml-cpu: detect correct cpu flags for arm64 (#16229) (#16239)" Build on RISCV Linux Machine by Cloud-V #3626: Pull request #17084 opened by angt
8m 40s angt:revert-ggml-cpu-detect-correct-cpu-flags-for-arm64-16229-16239
angt:revert-ggml-cpu-detect-correct-cpu-flags-for-arm64-16229-16239
8m 40s
kv-cache : pad the cache size to 256 for performance Build on RISCV Linux Machine by Cloud-V #3625: Pull request #17046 synchronize by ggerganov
6m 10s gg/iswa-pad-256
gg/iswa-pad-256
6m 10s
kv-cache : pad the cache size to 256 for performance Build on RISCV Linux Machine by Cloud-V #3624: Pull request #17046 synchronize by ggerganov
6m 20s gg/iswa-pad-256
gg/iswa-pad-256
6m 20s
convert: (demo) repacking compressed_tensor format of kimi-k2 Build on RISCV Linux Machine by Cloud-V #3623: Pull request #17083 opened by ngxson
6m 2s ngxson:xsn/convert_kimi_k2_quant_repack
ngxson:xsn/convert_kimi_k2_quant_repack
6m 2s
fixed a missing case for transposed copy Build on RISCV Linux Machine by Cloud-V #3622: Pull request #17081 opened by bssrdf
3m 10s bssrdf:cuda-transpose-cpy-hotfix
bssrdf:cuda-transpose-cpy-hotfix
3m 10s
arg: add --cache-list argument to list cached models Build on RISCV Linux Machine by Cloud-V #3621: Pull request #17073 reopened by ngxson
4m 49s ngxson:xsn/cache_model_list
ngxson:xsn/cache_model_list
4m 49s
arg: add --cache-list argument to list cached models Build on RISCV Linux Machine by Cloud-V #3620: Pull request #17073 synchronize by ngxson
3m 49s ngxson:xsn/cache_model_list
ngxson:xsn/cache_model_list
3m 49s
arg: add --cache-list argument to list cached models Build on RISCV Linux Machine by Cloud-V #3619: Pull request #17073 synchronize by ngxson
3m 9s ngxson:xsn/cache_model_list
ngxson:xsn/cache_model_list
3m 9s
CUDA: skip fusion for repeating adds in bias Build on RISCV Linux Machine by Cloud-V #3618: Pull request #17080 opened by am17an
3m 7s am17an:cuda-fix-bias-fusion
am17an:cuda-fix-bias-fusion
3m 7s
ggml-hexagon: fix test-backend-ops failures on specific binary ops Build on RISCV Linux Machine by Cloud-V #3617: Pull request #17042 synchronize by chraac
15m 6s chraac:dev-fix-test-failure
chraac:dev-fix-test-failure
15m 6s
server : handle failures to restore host cache Build on RISCV Linux Machine by Cloud-V #3616: Pull request #17078 opened by ggerganov
38m 32s gg/server-cache-failures
gg/server-cache-failures
38m 32s