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
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
mtmd: Add DeepSeekOCR Support Build on RISCV Linux Machine by Cloud-V #5172: Pull request #17400 synchronize by sfallah
1m 41s sfallah:sf/deepseek-ocr
sfallah:sf/deepseek-ocr
1m 41s
vulkan: add more num_blocks instantiations in rms_norm Build on RISCV Linux Machine by Cloud-V #5171: Pull request #17701 opened by jeffbolznv
1m 57s jeffbolznv:rms_norm_more_cases
jeffbolznv:rms_norm_more_cases
1m 57s
llama-server: fix duplicate HTTP headers in multiple models mode Build on RISCV Linux Machine by Cloud-V #5170: Pull request #17698 synchronize by ServeurpersoCom
1m 47s ServeurpersoCom:fix-duplicate-headers
ServeurpersoCom:fix-duplicate-headers
1m 47s
vulkan: perf_logger improvements Build on RISCV Linux Machine by Cloud-V #5169: Pull request #17672 synchronize by jeffbolznv
1m 40s jeffbolznv:perf_logger
jeffbolznv:perf_logger
1m 40s
vulkan: fix top_k bug when there are ties in the input Build on RISCV Linux Machine by Cloud-V #5168: Pull request #17659 synchronize by jeffbolznv
2m 32s jeffbolznv:topk_ties
jeffbolznv:topk_ties
2m 32s
llama-server: fix duplicate HTTP headers in multiple models mode Build on RISCV Linux Machine by Cloud-V #5167: Pull request #17698 opened by ServeurpersoCom
1m 58s ServeurpersoCom:fix-duplicate-headers
ServeurpersoCom:fix-duplicate-headers
1m 58s
server: add --media-path for local media files Build on RISCV Linux Machine by Cloud-V #5166: Pull request #17697 synchronize by ngxson
1m 59s ngxson:xsn/local_media_path
ngxson:xsn/local_media_path
1m 59s
server: add --media-path for local media files Build on RISCV Linux Machine by Cloud-V #5165: Pull request #17697 opened by ngxson
1m 42s ngxson:xsn/local_media_path
ngxson:xsn/local_media_path
1m 42s
sampling : add support for backend sampling Build on RISCV Linux Machine by Cloud-V #5164: Pull request #17004 synchronize by danbev
1m 45s danbev:gpu-sampling
danbev:gpu-sampling
1m 45s
mtmd: fix --no-warmup Build on RISCV Linux Machine by Cloud-V #5163: Pull request #17695 opened by ngxson
1m 43s ngxson:xsn/mtmd_fix_no_warmup
ngxson:xsn/mtmd_fix_no_warmup
1m 43s
vulkan: set all memory allocations to high priority Build on RISCV Linux Machine by Cloud-V #5162: Pull request #17624 synchronize by jeffbolznv
1m 40s jeffbolznv:priority
jeffbolznv:priority
1m 40s
Add support for CUMSUM and TRI for CUDA. Build on RISCV Linux Machine by Cloud-V #5161: Pull request #17584 synchronize by pwilkin
5m 46s pwilkin:tri_cumsum_cuda
pwilkin:tri_cumsum_cuda
5m 46s
Q4/Q8 Tiled Gemm Optimization. Build on RISCV Linux Machine by Cloud-V #5160: Pull request #16999 synchronize by shalinib-ibm
1m 43s shalinib-ibm:q8_q4_opt
shalinib-ibm:q8_q4_opt
1m 43s
Q4/Q8 Tiled Gemm Optimization. Build on RISCV Linux Machine by Cloud-V #5159: Pull request #16999 synchronize by shalinib-ibm
1m 44s shalinib-ibm:q8_q4_opt
shalinib-ibm:q8_q4_opt
1m 44s
Q4/Q8 Tiled Gemm Optimization. Build on RISCV Linux Machine by Cloud-V #5158: Pull request #16999 synchronize by shalinib-ibm
1m 48s shalinib-ibm:q8_q4_opt
shalinib-ibm:q8_q4_opt
1m 48s
Q4/Q8 Tiled Gemm Optimization. Build on RISCV Linux Machine by Cloud-V #5157: Pull request #16999 synchronize by shalinib-ibm
1m 40s shalinib-ibm:q8_q4_opt
shalinib-ibm:q8_q4_opt
1m 40s
Add support for CUMSUM and TRI for CUDA. Build on RISCV Linux Machine by Cloud-V #5156: Pull request #17584 synchronize by pwilkin
1m 46s pwilkin:tri_cumsum_cuda
pwilkin:tri_cumsum_cuda
1m 46s
Q4/Q8 Tiled Gemm Optimization. Build on RISCV Linux Machine by Cloud-V #5155: Pull request #16999 synchronize by shalinib-ibm
1m 43s shalinib-ibm:q8_q4_opt
shalinib-ibm:q8_q4_opt
1m 43s
model : add ASR support for LFM2-Audio-1.5B Build on RISCV Linux Machine by Cloud-V #5154: Pull request #17694 opened by tdakhran
1m 43s Liquid4All:tarek/feat/lfm2-asr-upstream
Liquid4All:tarek/feat/lfm2-asr-upstream
1m 43s
Add support for CUMSUM and TRI for CUDA. Build on RISCV Linux Machine by Cloud-V #5153: Pull request #17584 synchronize by pwilkin
1m 49s pwilkin:tri_cumsum_cuda
pwilkin:tri_cumsum_cuda
1m 49s
CUDA: generalized (mma) FA, add Volta support Build on RISCV Linux Machine by Cloud-V #5152: Pull request #17505 synchronize by JohannesGaessler
1m 44s JohannesGaessler:cuda-fa-mma-update-5
JohannesGaessler:cuda-fa-mma-update-5
1m 44s
ggml-zendnn : add ZenDNN backend for AMD CPUs Build on RISCV Linux Machine by Cloud-V #5151: Pull request #17690 opened by z-vishal
1m 47s z-vishal:ggml-zendnn
z-vishal:ggml-zendnn
1m 47s
Use OpenAI-compatible /v1/models endpoint by default Build on RISCV Linux Machine by Cloud-V #5150: Pull request #17689 opened by allozaur
1m 47s allozaur:allozaur/models-endpoint-openai-compat
allozaur:allozaur/models-endpoint-openai-compat
1m 47s
Fix unreadable user markdown colors and truncate long texts in deletion dialogs Build on RISCV Linux Machine by Cloud-V #5149: Pull request #17555 synchronize by ServeurpersoCom
2m 3s ServeurpersoCom:webui-cosmetic
ServeurpersoCom:webui-cosmetic
2m 3s
webui: Fix zero pasteLongTextToFileLen to disable conversion being overridden Build on RISCV Linux Machine by Cloud-V #5148: Pull request #17445 synchronize by awasisto
1m 45s awasisto:master
awasisto:master
1m 45s