Skip to content

Actions: petabridge/netclaw-inference

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
52 workflow runs
52 workflow runs

Filter by Workflow

⌥ + click/return to exclude

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
Build candidate from images/nvidia/dgx-spark/glm-5.3-flash-exl3/image.json at ce83cfb730236acef0b3a68f6ce6ff0152077789 Build inference image candidate #13: Manually run by Aaronontheweb
15m 6s master
master
15m 6s
feat(dgx-spark): add GLM-5.3-Flash EXL3 image for two DGX Sparks (#18) Validate inference images #38: Commit ce83cfb pushed by Aaronontheweb
10s master
master
10s
feat(dgx-spark): add GLM-5.3-Flash EXL3 image for two DGX Sparks Validate inference images #37: Pull request #18 opened by Aaronontheweb
10s feature/glm-5.3-flash-exl3-image
feature/glm-5.3-flash-exl3-image
10s
Promote images/amd/rocm/llama-cpp-gfx1201-avx2/image.json sha256:8125ad0877e980c8d8bc2d9da44074b13e66faf22ed22b225306a267f5d38370 as v0.1.0 Promote inference image digest #1: Manually run by Aaronontheweb
32s master
master
32s
release: date v0.1.0 (2026-08-14) for image promotion (#17) Validate inference images #36: Commit 37e0129 pushed by Aaronontheweb
14s master
master
14s
release: date v0.1.0 for llama-cpp-rocm-gfx1201-avx2 promotion Validate inference images #35: Pull request #17 opened by Aaronontheweb
15s release/llama-cpp-v0.1.0
release/llama-cpp-v0.1.0
15s
fix(amd/rocm): register /opt/llama.cpp/lib with ldconfig for runtime … Validate inference images #34: Commit 98e4410 pushed by Aaronontheweb
12s master
master
12s
Build candidate from images/amd/rocm/llama-cpp-gfx1201-avx2/image.json at 98e441024d79501570ac4de1769b2eeaec8c8fa8 Build inference image candidate #12: Manually run by Aaronontheweb
21m 15s master
master
21m 15s
Fix llama.cpp ROCm image: ldconfig for runtime library resolution Validate inference images #33: Pull request #16 opened by Aaronontheweb
13s fix/amd-rocm-ldconfig
fix/amd-rocm-ldconfig
13s
fix(amd/rocm): build full llama.cpp target set so cmake --install suc… Validate inference images #32: Commit 85b5db6 pushed by Aaronontheweb
20s master
master
20s
Build candidate from images/amd/rocm/llama-cpp-gfx1201-avx2/image.json at 85b5db69b42fffbca88a554913239958f66cdd86 Build inference image candidate #11: Manually run by Aaronontheweb
14m 46s master
master
14m 46s
Fix llama.cpp ROCm build: install full target set Validate inference images #31: Pull request #15 opened by Aaronontheweb
13s fix/amd-rocm-install-all-targets
fix/amd-rocm-install-all-targets
13s
Build candidate from images/amd/rocm/llama-cpp-gfx1201-avx2/image.json at b5bd0076f92588043b826f45ed6cfef3ffb3c303 Build inference image candidate #10: Manually run by Aaronontheweb
14m 39s master
master
14m 39s
fix(amd/rocm): install rocBLAS/hipBLAS dev libs; single-stage build (… Validate inference images #30: Commit b5bd007 pushed by Aaronontheweb
15s master
master
15s
Fix llama.cpp ROCm build: install rocBLAS/hipBLAS dev libs Validate inference images #29: Pull request #14 opened by Aaronontheweb
17s fix/amd-rocm-hipblas-dev
fix/amd-rocm-hipblas-dev
17s
Build candidate from images/amd/rocm/llama-cpp-gfx1201-avx2/image.json at 0cde9c868e379475fc60b77f61e32517f54e75d3 Build inference image candidate #9: Manually run by Aaronontheweb
1m 24s master
master
1m 24s
fix(amd/rocm): run llama.cpp image build under bash so pipefail/[[ ]]… Validate inference images #28: Commit 0cde9c8 pushed by Aaronontheweb
11s master
master
11s
Fix llama.cpp ROCm image build: run under bash (pipefail) Validate inference images #27: Pull request #13 opened by Aaronontheweb
15s fix/amd-rocm-dockerfile-shell
fix/amd-rocm-dockerfile-shell
15s
Build candidate from images/amd/rocm/llama-cpp-gfx1201-avx2/image.json at 111c1ae59079d4ea44e190e9570b9acb82634a92 Build inference image candidate #8: Manually run by Aaronontheweb
1m 2s master
master
1m 2s
feat(amd/rocm): add AVX2-baseline llama.cpp gfx1201 image + platform-… Validate inference images #26: Commit 111c1ae pushed by Aaronontheweb
22s master
master
22s
Add AVX2-baseline llama.cpp gfx1201 ROCm image + platform-aware build runner Validate inference images #25: Pull request #12 opened by Aaronontheweb
10s feature/amd-rocm-llama-cpp-avx2
feature/amd-rocm-llama-cpp-avx2
10s
Build candidate from images/nvidia/dgx-spark/deepseek-v4-flash-0731/image.json at 2d22ab281f4cf9279f40814e0840ad560f8a00ec Build inference image candidate #7: Manually run by Aaronontheweb
5m 50s master
master
5m 50s
fix: warm 512-wide sparse MLA kernels (#11) Validate inference images #24: Commit 2d22ab2 pushed by Aaronontheweb
25s master
master
25s
Warm 512-wide DeepSeek sparse-MLA kernels before serving Validate inference images #23: Pull request #11 opened by Aaronontheweb
17s fix/warm-512-sparse-mla
fix/warm-512-sparse-mla
17s
Fix capitalization of 'Netclaw' in README Validate inference images #22: Commit bc80c3c pushed by Aaronontheweb
20s master
master
20s