Skip to content

Actions: SharpAI/mlx-swift-lm

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
900 workflow runs
900 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
🔄 Auto-Sync Upstream 🔄 Auto-Sync Upstream #185: Scheduled
14s main
main
14s
🔄 Auto-Sync Upstream 🔄 Auto-Sync Upstream #184: Scheduled
11s main
main
11s
Merge pull request #80 from SharpAI/fix/preload-non-expert-weights CI #264: Commit 4f1fdaa pushed by solderzzc
23m 53s main
main
23m 53s
Merge pull request #80 from SharpAI/fix/preload-non-expert-weights Auto Release Pipeline #65: Commit 4f1fdaa pushed by solderzzc
18s main
main
18s
fix(streaming): read non-expert weights before serving (GPU watchdog timeout on cold start) CI #263: Pull request #80 opened by solderzzc
28m 0s fix/preload-non-expert-weights
fix/preload-non-expert-weights
28m 0s
fix(streaming): read non-expert weights before serving (GPU watchdog timeout on cold start) Build and Test #198: Pull request #80 opened by solderzzc
1s fix/preload-non-expert-weights
fix/preload-non-expert-weights
1s
fix(streaming): read non-expert weights before serving (GPU watchdog timeout on cold start) Downstream Integration Test #172: Pull request #80 opened by solderzzc
11m 8s fix/preload-non-expert-weights
fix/preload-non-expert-weights
11m 8s
Merge pull request #79 from SharpAI/fix/stacked-moe-unsorted-slots Auto Release Pipeline #64: Commit 9da07be pushed by solderzzc
20s main
main
20s
Merge pull request #79 from SharpAI/fix/stacked-moe-unsorted-slots CI #262: Commit 9da07be pushed by solderzzc
28m 11s main
main
28m 11s
fix(moe): stacked LRU slot ids must not be declared sorted (mlx 0.32) Build and Test #197: Pull request #79 opened by solderzzc
2s fix/stacked-moe-unsorted-slots
fix/stacked-moe-unsorted-slots
2s
fix(moe): stacked LRU slot ids must not be declared sorted (mlx 0.32) CI #261: Pull request #79 opened by solderzzc
25m 49s fix/stacked-moe-unsorted-slots
fix/stacked-moe-unsorted-slots
25m 49s
fix(moe): stacked LRU slot ids must not be declared sorted (mlx 0.32) Downstream Integration Test #171: Pull request #79 opened by solderzzc
12m 13s fix/stacked-moe-unsorted-slots
fix/stacked-moe-unsorted-slots
12m 13s
🔄 Auto-Sync: ml-explore/mlx-swift-lm main (a1f575d, 3 commit(s)) Downstream Integration Test #170: Pull request #78 opened by github-actions Bot
12m 52s bot/upstream-a1f575d-a8c85d5
bot/upstream-a1f575d-a8c85d5
12m 52s
🔄 Auto-Sync: ml-explore/mlx-swift-lm main (a1f575d, 3 commit(s)) CI #260: Pull request #78 opened by github-actions Bot
24m 40s bot/upstream-a1f575d-a8c85d5
bot/upstream-a1f575d-a8c85d5
24m 40s
🔄 Auto-Sync: ml-explore/mlx-swift-lm main (a1f575d, 3 commit(s)) Build and Test #196: Pull request #78 opened by github-actions Bot
1m 9s bot/upstream-a1f575d-a8c85d5
bot/upstream-a1f575d-a8c85d5
1m 9s
🔄 Auto-Sync Upstream 🔄 Auto-Sync Upstream #183: Scheduled
47s main
main
47s
Merge pull request #77 from CodeAndCanvas728/perf/qwen35-skip-moe-flu… CI #259: Commit a8c85d5 pushed by solderzzc
39m 31s main
main
39m 31s
Merge pull request #77 from CodeAndCanvas728/perf/qwen35-skip-moe-flu… Auto Release Pipeline #63: Commit a8c85d5 pushed by solderzzc
18s main
main
18s
perf(qwen35): skip the per-layer MoE GPU flush on single-token decode CI #258: Pull request #77 synchronize by solderzzc
32m 40s CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
32m 40s
perf(qwen35): skip the per-layer MoE GPU flush on single-token decode Downstream Integration Test #169: Pull request #77 synchronize by solderzzc
9m 20s CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
9m 20s
perf(qwen35): skip the per-layer MoE GPU flush on single-token decode Build and Test #195: Pull request #77 synchronize by solderzzc
3s CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
3s
perf(qwen35): skip the per-layer MoE GPU flush on single-token decode CI #257: Pull request #77 opened by CodeAndCanvas728
25m 45s CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
25m 45s
perf(qwen35): skip the per-layer MoE GPU flush on single-token decode Downstream Integration Test #168: Pull request #77 opened by CodeAndCanvas728
13m 17s CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
13m 17s
perf(qwen35): skip the per-layer MoE GPU flush on single-token decode Build and Test #194: Pull request #77 opened by CodeAndCanvas728
3s CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
CodeAndCanvas728:perf/qwen35-skip-moe-flush-on-decode
3s
Merge pull request #76 from SharpAI/sync/upstream-ecd8e88-merge Auto Release Pipeline #62: Commit 6490e3f pushed by solderzzc
19s main
main
19s