Skip to content

Actions: dkurukula/colibri

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
69 workflow runs
69 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
glm53: size the OpenMP team to physical cores, not logical CI #34: Pull request #20 opened by dkurukula
2m 54s fix/glm53-omp-thread-sizing
fix/glm53-omp-thread-sizing
2m 54s
glm53: size the OpenMP team to physical cores, not logical check #34: Pull request #20 opened by dkurukula
5m 50s fix/glm53-omp-thread-sizing
fix/glm53-omp-thread-sizing
5m 50s
Shrink expert cache slots on reuse, not just grow them check #33: Pull request #19 opened by dkurukula
6m 17s fix-expert-slab-shrink
fix-expert-slab-shrink
6m 17s
Shrink expert cache slots on reuse, not just grow them CI #33: Pull request #19 opened by dkurukula
2m 12s fix-expert-slab-shrink
fix-expert-slab-shrink
2m 12s
Fix decode heartbeat mislabeling small prefills as [decode] CI #32: Pull request #18 opened by dkurukula
2m 37s fix-decode-heartbeat-mislabel
fix-decode-heartbeat-mislabel
2m 37s
Fix decode heartbeat mislabeling small prefills as [decode] check #32: Pull request #18 opened by dkurukula
5m 34s fix-decode-heartbeat-mislabel
fix-decode-heartbeat-mislabel
5m 34s
Merge pull request #17 from dkurukula/reconcile-glm53-deps check #31: Commit eebc8be pushed by dkurukula
6m 24s main
main
6m 24s
Merge pull request #17 from dkurukula/reconcile-glm53-deps CI #31: Commit eebc8be pushed by dkurukula
2m 26s main
main
2m 26s
Reconcile glm53.c dependencies into main, fix MLA OpenMP thrash, land CUDA expert streaming CI #30: Pull request #17 opened by dkurukula
2m 32s reconcile-glm53-deps
reconcile-glm53-deps
2m 32s
Reconcile glm53.c dependencies into main, fix MLA OpenMP thrash, land CUDA expert streaming check #30: Pull request #17 opened by dkurukula
6m 17s reconcile-glm53-deps
reconcile-glm53-deps
6m 17s
Merge pull request #15 from dkurukula/docs-fork-attribution CI #29: Commit f35076a pushed by dkurukula
2m 29s main
main
2m 29s
Merge pull request #15 from dkurukula/docs-fork-attribution check #29: Commit f35076a pushed by dkurukula
6m 12s main
main
6m 12s
README: make clear this is a fork, attribute upstream content explicitly CI #28: Pull request #15 opened by dkurukula
2m 31s docs-fork-attribution
docs-fork-attribution
2m 31s
README: make clear this is a fork, attribute upstream content explicitly check #28: Pull request #15 opened by dkurukula
6m 15s docs-fork-attribution
docs-fork-attribution
6m 15s
Merge pull request #14 from dkurukula/cuda-miss-cpu-gpu-split check #27: Commit fc98cfd pushed by dkurukula
6m 3s main
main
6m 3s
Merge pull request #14 from dkurukula/cuda-miss-cpu-gpu-split CI #27: Commit fc98cfd pushed by dkurukula
2m 27s main
main
2m 27s
Fixed-ratio CPU/GPU concurrent split for decode misses (COLI_MISS_CPU_EVERY) check #26: Pull request #14 opened by dkurukula
6m 10s cuda-miss-cpu-gpu-split
cuda-miss-cpu-gpu-split
6m 10s
Fixed-ratio CPU/GPU concurrent split for decode misses (COLI_MISS_CPU_EVERY) CI #26: Pull request #14 opened by dkurukula
2m 28s cuda-miss-cpu-gpu-split
cuda-miss-cpu-gpu-split
2m 28s
Merge pull request #12 from dkurukula/cuda-miss-async-pipeline check #25: Commit a587e9d pushed by dkurukula
6m 39s main
main
6m 39s
Merge pull request #12 from dkurukula/cuda-miss-async-pipeline CI #25: Commit a587e9d pushed by dkurukula
2m 35s main
main
2m 35s
Async double-buffered dispatch for CUDA_MISS_GPU decode misses CI #24: Pull request #12 synchronize by dkurukula
2m 32s cuda-miss-async-pipeline
cuda-miss-async-pipeline
2m 32s
Async double-buffered dispatch for CUDA_MISS_GPU decode misses check #24: Pull request #12 synchronize by dkurukula
5m 15s cuda-miss-async-pipeline
cuda-miss-async-pipeline
5m 15s
Async double-buffered dispatch for CUDA_MISS_GPU decode misses check #23: Pull request #12 synchronize by dkurukula
6m 22s cuda-miss-async-pipeline
cuda-miss-async-pipeline
6m 22s
Async double-buffered dispatch for CUDA_MISS_GPU decode misses CI #23: Pull request #12 synchronize by dkurukula
2m 32s cuda-miss-async-pipeline
cuda-miss-async-pipeline
2m 32s
Async double-buffered dispatch for CUDA_MISS_GPU decode misses CI #22: Pull request #12 opened by dkurukula
2m 7s cuda-miss-async-pipeline
cuda-miss-async-pipeline
2m 7s