Skip to content

Actions: FluffyAIcode/Kakeya-LLM-Inference-engine

Actions

Integration (Mac M4)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
integration.yaml
274 workflow runs
274 workflow runs

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
Harden Primary decode lifecycle and isolate MLX worker Integration (Mac M4) #224: Pull request #227 opened by FluffyAIcode
1m 52s agent/primary-decode-worker-acceptance-integration-0721
agent/primary-decode-worker-acceptance-integration-0721
1m 52s
fix(prefill): inject immutable retained-token cap Integration (Mac M4) #223: Pull request #201 synchronize by FluffyAIcode
1m 48s AgentMemory/explicit-retained-token-cap-0719
AgentMemory/explicit-retained-token-cap-0719
1m 48s
fix(prefill): inject immutable retained-token cap Integration (Mac M4) #222: Pull request #201 opened by FluffyAIcode
1m 57s AgentMemory/explicit-retained-token-cap-0719
AgentMemory/explicit-retained-token-cap-0719
1m 57s
fix(prefill): cap reservation at sliding window Integration (Mac M4) #221: Pull request #198 opened by FluffyAIcode
2m 4s AgentMemory/window-aware-snapshot-estimate-0718
AgentMemory/window-aware-snapshot-estimate-0718
2m 4s
perf(prefill): segment long jobs for autoresearch Integration (Mac M4) #220: Pull request #192 synchronize by FluffyAIcode
1m 46s AgentMemory/prefill-autoresearch-segments-0717
AgentMemory/prefill-autoresearch-segments-0717
1m 46s
perf(prefill): segment long jobs for autoresearch Integration (Mac M4) #219: Pull request #192 opened by FluffyAIcode
1m 57s AgentMemory/prefill-autoresearch-segments-0717
AgentMemory/prefill-autoresearch-segments-0717
1m 57s
perf(prefill): export only final MLX snapshot Integration (Mac M4) #218: Pull request #191 opened by FluffyAIcode
2m 1s AgentMemory/final-only-prefill-snapshot-0717
AgentMemory/final-only-prefill-snapshot-0717
2m 1s
fix(prefill): preserve unrelated snapshots during jobs Integration (Mac M4) #217: Pull request #188 opened by FluffyAIcode
1m 55s AgentMemory/precise-snapshot-reservation-0717
AgentMemory/precise-snapshot-reservation-0717
1m 55s
fix(prefill): atomically reserve and publish snapshots Integration (Mac M4) #216: Pull request #187 synchronize by FluffyAIcode
1m 49s AgentMemory/atomic-prefill-snapshot-0717
AgentMemory/atomic-prefill-snapshot-0717
1m 49s
fix(prefill): atomically reserve and publish snapshots Integration (Mac M4) #215: Pull request #187 opened by FluffyAIcode
1m 56s AgentMemory/atomic-prefill-snapshot-0717
AgentMemory/atomic-prefill-snapshot-0717
1m 56s
fix(agents): require full-context semantic Critic review Integration (Mac M4) #214: Pull request #184 opened by FluffyAIcode
1m 58s AgentMemory/full-context-critic-0717
AgentMemory/full-context-critic-0717
1m 58s
fix(agents): bound Critic evidence prefill context Integration (Mac M4) #213: Pull request #181 opened by FluffyAIcode
1m 53s AgentMemory/critic-evidence-window-0717
AgentMemory/critic-evidence-window-0717
1m 53s
fix(agents): complete responses to EOS and ground critique Integration (Mac M4) #212: Pull request #178 opened by FluffyAIcode
2m 5s AgentMemory/agent-completion-rubric-0716
AgentMemory/agent-completion-rubric-0716
2m 5s
feat(agents): add Generator-Critic inference demo Integration (Mac M4) #211: Pull request #175 opened by FluffyAIcode
1m 51s AgentMemory/agent-gan-inference-demo-0716
AgentMemory/agent-gan-inference-demo-0716
1m 51s
feat(bench): add three-phase prefill fleet benchmark Integration (Mac M4) #210: Pull request #174 opened by FluffyAIcode
1m 49s AgentMemory/prefill-benchmark-task-0716
AgentMemory/prefill-benchmark-task-0716
1m 49s
fix(prefill): resolve promoted final snapshots directly Integration (Mac M4) #209: Pull request #173 opened by FluffyAIcode
2m 5s AgentMemory/sparse-hot-kv-lookup-0716
AgentMemory/sparse-hot-kv-lookup-0716
2m 5s
fix(prefill): isolate cache budget policy from MLX runtime Integration (Mac M4) #208: Pull request #172 opened by FluffyAIcode
1m 47s AgentMemory/tiered-kv-offload-0716
AgentMemory/tiered-kv-offload-0716
1m 47s
feat(prefill): add tiered KV hot promotion and offload Integration (Mac M4) #207: Pull request #171 opened by FluffyAIcode
1m 55s AgentMemory/tiered-kv-offload-0716
AgentMemory/tiered-kv-offload-0716
1m 55s
feat(prefill): enforce decode-only primary mode Integration (Mac M4) #206: Pull request #170 opened by FluffyAIcode
1m 59s AgentMemory/primary-decode-allens-prefill-0716
AgentMemory/primary-decode-allens-prefill-0716
1m 59s
feat(prefill): add maintenance cache saturation harness Integration (Mac M4) #205: Pull request #169 opened by FluffyAIcode
1m 41s AgentMemory/kv-cache-saturation-harness-0712
AgentMemory/kv-cache-saturation-harness-0712
1m 41s
feat(prefill): add bit-packed KakeyaLattice snapshots Integration (Mac M4) #204: Pull request #167 opened by FluffyAIcode
1m 43s AgentMemory/prefill-kakeyalattice-codec-0712
AgentMemory/prefill-kakeyalattice-codec-0712
1m 43s
fix(prefill): keep MLX worker compute thread-affine Integration (Mac M4) #203: Pull request #165 opened by FluffyAIcode
1m 40s AgentMemory/mlx-prefill-worker-thread-affinity-0712
AgentMemory/mlx-prefill-worker-thread-affinity-0712
1m 40s
feat(prefill): operationalize remote MLX workers Integration (Mac M4) #202: Pull request #164 opened by FluffyAIcode
1m 41s AgentMemory/prefill-worker-production-completion-0712
AgentMemory/prefill-worker-production-completion-0712
1m 41s
feat(distributed): orchestrate same-model prefill workers and KV memory tier Integration (Mac M4) #201: Pull request #160 synchronize by cursor Bot
2m 18s AgentMemory/prefill-worker-orchestration-2815
AgentMemory/prefill-worker-orchestration-2815
2m 18s
feat(distributed): orchestrate same-model prefill workers and KV memory tier Integration (Mac M4) #200: Pull request #160 synchronize by cursor Bot
43s AgentMemory/prefill-worker-orchestration-2815
AgentMemory/prefill-worker-orchestration-2815
43s