Skip to content

Actions: InfiniTensor/InfiniOps

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ 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
feat(moore): support paged flash attention decode (#962) CI #1345: Commit 5d32b52 pushed by voltjia
Queued master
master
Queued
feat(moore): support paged flash attention decode (#962) CI v2 Shadow #989: Commit 5d32b52 pushed by voltjia
Queued master
master
Queued
feat(moore): support paged flash attention decode (#962) Clang Format #10318: Commit 5d32b52 pushed by voltjia
4m 2s master
master
4m 2s
feat(moore): support paged flash attention decode (#962) Documentation Pages #537: Commit 5d32b52 pushed by voltjia
1m 21s master
master
1m 21s
feat(moore): support paged flash attention decode (#962) Ruff #10321: Commit 5d32b52 pushed by voltjia
11s master
master
11s
feat(moore): support paged flash attention decode CI v2 Shadow #988: Pull request #962 synchronize by voltjia
Queued feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
Queued
feat(moore): support paged flash attention decode CI #1344: Pull request #962 synchronize by voltjia
Queued feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
Queued
feat(moore): support paged flash attention decode Documentation Pages #536: Pull request #962 synchronize by voltjia
1m 8s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
1m 8s
feat(moore): support paged flash attention decode Clang Format #10317: Pull request #962 synchronize by voltjia
5m 49s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
5m 49s
feat(moore): support paged flash attention decode Ruff #10320: Pull request #962 synchronize by voltjia
14s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
14s
test: share flash attention KV-cache coverage Ruff #10319: Commit 65e2293 pushed by voltjia
10s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
10s
test: share flash attention KV-cache coverage Clang Format #10316: Commit 65e2293 pushed by voltjia
9m 36s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
9m 36s
feat(moore): support paged flash attention decode CI v2 Shadow #987: Pull request #962 synchronize by voltjia
20m 18s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
20m 18s
feat(moore): support paged flash attention decode CI #1343: Pull request #962 synchronize by voltjia
19m 15s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
19m 15s
feat(moore): support paged flash attention decode Documentation Pages #535: Pull request #962 synchronize by voltjia
1m 5s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
1m 5s
feat(moore): support paged flash attention decode Clang Format #10315: Pull request #962 synchronize by voltjia
4m 16s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
4m 16s
feat(moore): support paged flash attention decode Ruff #10318: Pull request #962 synchronize by voltjia
17s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
17s
test: share flash attention KV-cache coverage Clang Format #10314: Commit 32647b8 pushed by voltjia
13m 59s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
13m 59s
test: share flash attention KV-cache coverage Ruff #10317: Commit 32647b8 pushed by voltjia
18s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
18s
feat(iluvatar): add native canonical attention providers CI v2 Shadow #986: Pull request #975 synchronize by gongchensu
Queued gongchensu:feat/iluvatar-canonical-attention
gongchensu:feat/iluvatar-canonical-attention
Queued
feat(iluvatar): add native canonical attention providers CI #1342: Pull request #975 synchronize by gongchensu
Queued gongchensu:feat/iluvatar-canonical-attention
gongchensu:feat/iluvatar-canonical-attention
Queued
feat(iluvatar): add native canonical attention providers Ruff #10316: Pull request #975 synchronize by gongchensu
12s gongchensu:feat/iluvatar-canonical-attention
gongchensu:feat/iluvatar-canonical-attention
12s
feat(iluvatar): add native canonical attention providers Clang Format #10313: Pull request #975 synchronize by gongchensu
4m 11s gongchensu:feat/iluvatar-canonical-attention
gongchensu:feat/iluvatar-canonical-attention
4m 11s
feat(iluvatar): add native canonical attention providers Documentation Pages #534: Pull request #975 synchronize by gongchensu
59s gongchensu:feat/iluvatar-canonical-attention
gongchensu:feat/iluvatar-canonical-attention
59s
feat(moore): support paged flash attention decode CI #1341: Pull request #962 synchronize by voltjia
8h 18m 29s feat/moore-flash-attn-kvcache
feat/moore-flash-attn-kvcache
8h 18m 29s