Skip to content

Actions: EfficientMoE/MoE-Infinity

Actions

Formatting

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit-format.yml
560 workflow runs
560 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
fix(contextpilot): stop spurious WARNING on single-prompt completion optimize (#146 Bug 3) Formatting #723: Pull request #149 synchronize by drunkcoding
45s fix/contextpilot-completion-empty-context
fix/contextpilot-completion-empty-context
45s
docs(design): PD-dflash-MoE serving design doc Formatting #722: Pull request #132 synchronize by drunkcoding
35s docs/pd-dflash-moe-design
docs/pd-dflash-moe-design
35s
Formatting Formatting #721: Scheduled
34s main
main
34s
Formatting Formatting #720: Scheduled
41s main
main
41s
fix(contextpilot): stop spurious WARNING on single-prompt completion optimize (#146 Bug 3) Formatting #719: Pull request #149 synchronize by drunkcoding
45s fix/contextpilot-completion-empty-context
fix/contextpilot-completion-empty-context
45s
fix(dflash): unblock Qwen3.5-MoE + DFlash + ContextPilot serving hang (multi-GPU device placement) Formatting #718: Pull request #147 synchronize by drunkcoding
39s fix/qwen35-dflash-multigpu-device-hang
fix/qwen35-dflash-multigpu-device-hang
39s
fix(contextpilot): stop spurious WARNING on single-prompt completion optimize (#146 Bug 3) Formatting #717: Pull request #149 synchronize by drunkcoding
35s fix/contextpilot-completion-empty-context
fix/contextpilot-completion-empty-context
35s
fix(serving): surface failed model init as UNHEALTHY instead of hanging (#146 Bug 2) Formatting #716: Pull request #148 synchronize by drunkcoding
39s fix/surface-failed-init-unhealthy
fix/surface-failed-init-unhealthy
39s
fix(dflash): unblock Qwen3.5-MoE + DFlash + ContextPilot serving hang (multi-GPU device placement) Formatting #715: Pull request #147 synchronize by drunkcoding
37s fix/qwen35-dflash-multigpu-device-hang
fix/qwen35-dflash-multigpu-device-hang
37s
fix(contextpilot): stop spurious WARNING on single-prompt completion optimize (#146 Bug 3) Formatting #714: Pull request #149 opened by drunkcoding
50s fix/contextpilot-completion-empty-context
fix/contextpilot-completion-empty-context
50s
fix(serving): surface failed model init as UNHEALTHY instead of hanging (#146 Bug 2) Formatting #713: Pull request #148 opened by drunkcoding
33s fix/surface-failed-init-unhealthy
fix/surface-failed-init-unhealthy
33s
fix(dflash): unblock Qwen3.5-MoE + DFlash + ContextPilot serving hang (multi-GPU device placement) Formatting #712: Pull request #147 opened by drunkcoding
59s fix/qwen35-dflash-multigpu-device-hang
fix/qwen35-dflash-multigpu-device-hang
59s
Formatting Formatting #711: Scheduled
45s main
main
45s
test(integration): per-model examples + GPU real-checkpoint smoke tests Formatting #710: Pull request #145 synchronize by drunkcoding
42s feat/model-examples-regression
feat/model-examples-regression
42s
test(integration): per-model examples + GPU real-checkpoint smoke tests Formatting #709: Pull request #145 opened by drunkcoding
35s feat/model-examples-regression
feat/model-examples-regression
35s
docs: add repository-wide feature and operations guides Formatting #708: Pull request #141 synchronize by drunkcoding
49s docs/repository-documentation
docs/repository-documentation
49s
docs: add repository-wide feature and operations guides Formatting #707: Pull request #141 synchronize by drunkcoding
16s docs/repository-documentation
docs/repository-documentation
16s
feat(dflash): converge DFlash spec-decode stack → dev (supersedes #140) Formatting #706: Pull request #143 opened by drunkcoding
51s feat/dflash-tracks-abcd
feat/dflash-tracks-abcd
51s
Formatting Formatting #705: Scheduled
43s main
main
43s
docs: add repository-wide feature and operations guides Formatting #704: Pull request #141 opened by drunkcoding
36s docs/repository-documentation
docs/repository-documentation
36s
docs(rfc): move model-topology logic from C++ to Python (design-only) Formatting #703: Pull request #133 synchronize by drunkcoding
40s refactor/topology-logic-python-extraction
refactor/topology-logic-python-extraction
40s
feat(dflash): converge spec-decode stack → dev (gpt-oss DFlash + route-ahead prototype + GLM-5.2 + perf-model) Formatting #702: Pull request #140 opened by drunkcoding
38s feat/dflash-spec-decode
feat/dflash-spec-decode
38s
feat(dflash): route-ahead prefetch, sampled/batched decoding, serving integration + drafter-driven contract Formatting #701: Pull request #139 synchronize by drunkcoding
35s feat/dflash-tracks-abcd
feat/dflash-tracks-abcd
35s
feat(dflash): route-ahead prefetch, sampled/batched decoding, serving integration + drafter-driven contract Formatting #700: Pull request #139 synchronize by drunkcoding
36s feat/dflash-tracks-abcd
feat/dflash-tracks-abcd
36s
Formatting Formatting #699: Scheduled
37s main
main
37s