Skip to content

Actions: microsoft/onnxruntime-genai

Actions

Linux CUDA x64 Build

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
linux-gpu-x64-build.yml
3,378 workflow runs
3,378 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

expose start/end profiling API in Models class Linux CUDA x64 Build #6428: Pull request #1898 opened by xiaofeihan1
11m 32s xiaofeihan/start_end_profile
xiaofeihan/start_end_profile
11m 32s
Implement Cast for webgpu Linux CUDA x64 Build #6427: Pull request #1895 synchronize by qjia7
31m 38s cast
cast
31m 38s
Add model builder for Qwen2_5_VLTextModel Linux CUDA x64 Build #6426: Pull request #1882 synchronize by tianleiwu
32m 53s tlwu/qwen_2_5_vl_txt_model_builder
tlwu/qwen_2_5_vl_txt_model_builder
32m 53s
Add model builder for Qwen2_5_VLTextModel Linux CUDA x64 Build #6425: Pull request #1882 synchronize by tianleiwu
26m 12s tlwu/qwen_2_5_vl_txt_model_builder
tlwu/qwen_2_5_vl_txt_model_builder
26m 12s
Add model builder for Qwen2_5_VLTextModel Linux CUDA x64 Build #6424: Pull request #1882 synchronize by tianleiwu
7m 7s tlwu/qwen_2_5_vl_txt_model_builder
tlwu/qwen_2_5_vl_txt_model_builder
7m 7s
Add model builder for Qwen2_5_VLTextModel Linux CUDA x64 Build #6423: Pull request #1882 synchronize by tianleiwu
2m 39s tlwu/qwen_2_5_vl_txt_model_builder
tlwu/qwen_2_5_vl_txt_model_builder
2m 39s
Extra_options disable_qkv_fusion to untie qkv_projs from upstream c… Linux CUDA x64 Build #6422: Commit 4f37298 pushed by tianleiwu
34m 39s main
main
34m 39s
Extra_options disable_qkv_fusion to untie qkv_projs from upstream choice Linux CUDA x64 Build #6421: Pull request #1893 synchronize by jixiongdeng
34m 10s jd/disable_fuse_qkv
jd/disable_fuse_qkv
34m 10s
whisper: Support a variant of the whisper pipeline where encoder / decoder are stateful. Linux CUDA x64 Build #6420: Pull request #1857 synchronize by RyanMetcalfeInt8
33m 51s RyanMetcalfeInt8:whisper_stateful_ov_support
RyanMetcalfeInt8:whisper_stateful_ov_support
33m 51s
Implement Cast for webgpu Linux CUDA x64 Build #6419: Pull request #1895 synchronize by qjia7
31m 49s cast
cast
31m 49s
Implement Cast for webgpu Linux CUDA x64 Build #6418: Pull request #1895 opened by qjia7
31m 41s cast
cast
31m 41s
Also clear provider_options when ClearProviders is called Linux CUDA x64 Build #6417: Pull request #1894 opened by Zhaeong
Action required AMD-GPU:amd/dev/ozhang/add_clear_provider_options
AMD-GPU:amd/dev/ozhang/add_clear_provider_options
Action required
Support pre-registered plug-in NvTensorRtRtx execution provider library Linux CUDA x64 Build #6416: Pull request #1889 synchronize by anujj
32m 56s anujj:ep_abi
anujj:ep_abi
32m 56s
Fix bug in Squeeze for getting the value of total_seq_len (#1886) Linux CUDA x64 Build #6415: Commit 5492721 pushed by kunal-vaishnavi
31m 38s main
main
31m 38s
Generic shared emb_tokens/lm_head implementation (#1885) Linux CUDA x64 Build #6414: Commit f748f24 pushed by kunal-vaishnavi
31m 42s main
main
31m 42s
Extra_options disable_qkv_fusion to untie qkv_projs from upstream choice Linux CUDA x64 Build #6413: Pull request #1893 synchronize by jixiongdeng
30m 22s jd/disable_fuse_qkv
jd/disable_fuse_qkv
30m 22s
Extra_options disable_qkv_fusion to untie qkv_projs from upstream choice Linux CUDA x64 Build #6412: Pull request #1893 opened by jixiongdeng
2m 58s jd/disable_fuse_qkv
jd/disable_fuse_qkv
2m 58s
whisper: Support a variant of the whisper pipeline where encoder / decoder are stateful. Linux CUDA x64 Build #6411: Pull request #1857 synchronize by RyanMetcalfeInt8
34m 24s RyanMetcalfeInt8:whisper_stateful_ov_support
RyanMetcalfeInt8:whisper_stateful_ov_support
34m 24s
Add processor for QWen 2.5 VL Linux CUDA x64 Build #6410: Pull request #1891 synchronize by tianleiwu
32m 54s tlwu/qwen
tlwu/qwen
32m 54s
Add model builder for Qwen2_5_VLTextModel Linux CUDA x64 Build #6409: Pull request #1882 synchronize by tianleiwu
32m 59s tlwu/qwen_2_5_vl_txt_model_builder
tlwu/qwen_2_5_vl_txt_model_builder
32m 59s
Add processor for QWen 2.5 VL Linux CUDA x64 Build #6408: Pull request #1891 synchronize by tianleiwu
2m 55s tlwu/qwen
tlwu/qwen
2m 55s
Lock transformers version to fix test pipeline Linux CUDA x64 Build #6407: Pull request #1892 opened by tianleiwu
32m 58s tlwu/pin_transformers
tlwu/pin_transformers
32m 58s
Generic shared emb_tokens/lm_head implementation Linux CUDA x64 Build #6406: Pull request #1885 synchronize by jixiongdeng
32m 41s jd/shared_emb
jd/shared_emb
32m 41s
Support pre-registered plug-in NvTensorRtRtx execution provider library Linux CUDA x64 Build #6405: Pull request #1889 synchronize by anujj
19m 9s anujj:ep_abi
anujj:ep_abi
19m 9s
Support pre-registered plug-in NvTensorRtRtx execution provider library Linux CUDA x64 Build #6404: Pull request #1889 synchronize by anujj
8m 10s anujj:ep_abi
anujj:ep_abi
8m 10s