Skip to content

Actions: ModelTC/LightLLM

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(cache): add exact hybrid checkpoints for agent continuations Pre-commit checks #5121: Pull request #1558 synchronize by sufubao
43s sufubao:cache-optim
sufubao:cache-optim
43s
feat(cache): add exact hybrid checkpoints for agent continuations Pre-commit checks #5120: Pull request #1558 synchronize by sufubao
41s sufubao:cache-optim
sufubao:cache-optim
41s
refactor: generalize hybrid attention checkpoint management Pre-commit checks #5119: Pull request #1559 opened by shihaobai
34s bsh/refactor-hybrid-cache
bsh/refactor-hybrid-cache
34s
feat(cache): add exact hybrid checkpoints for agent continuations Pre-commit checks #5118: Pull request #1558 opened by sufubao
48s sufubao:cache-optim
sufubao:cache-optim
48s
Support request-level cache for hybrid sliding-window attention Pre-commit checks #5117: Pull request #1545 synchronize by shihaobai
40s bsh/hybrid-sliding-window-cache
bsh/hybrid-sliding-window-cache
40s
Support request-level cache for hybrid sliding-window attention Pre-commit checks #5116: Pull request #1545 synchronize by shihaobai
37s bsh/hybrid-sliding-window-cache
bsh/hybrid-sliding-window-cache
37s
fix(server): stop bare excepts from swallowing cancellation and shutdown Pre-commit checks #5115: Pull request #1557 opened by harshadkhetpal
Action required harshadkhetpal:fix/server-bare-excepts
harshadkhetpal:fix/server-bare-excepts
Action required
feat(autotune): separate general and decode attention warmup (#1549) Docker #941: Commit 1eb4810 pushed by hiworldwzj
12m 18s main
main
12m 18s
Add P/D metrics aggregation endpoint to PD master Pre-commit checks #5114: Pull request #1556 opened by sufubao
36s sufubao:pd-master-metrics
sufubao:pd-master-metrics
36s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5113: Pull request #1549 synchronize by hiworldwzj
41s wzj_auto
wzj_auto
41s
feat(mtp): add optional ASD acceptance policy for greedy MTP verification Pre-commit checks #5112: Pull request #1555 opened by Kissmetothemoon
-1s Kissmetothemoon:asd-mtp-acceptance
Kissmetothemoon:asd-mtp-acceptance
-1s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5111: Pull request #1549 synchronize by shihaobai
37s wzj_auto
wzj_auto
37s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5110: Pull request #1549 synchronize by shihaobai
37s wzj_auto
wzj_auto
37s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5109: Pull request #1549 synchronize by hiworldwzj
37s wzj_auto
wzj_auto
37s
fix(sampling_params): reject out-of-range token ids at intake Pre-commit checks #5108: Pull request #1554 opened by SuperMarioYL
29s SuperMarioYL:fix/reject-out-of-range-token-ids
SuperMarioYL:fix/reject-out-of-range-token-ids
29s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5107: Pull request #1549 synchronize by hiworldwzj
38s wzj_auto
wzj_auto
38s
fix: ctrl c for single and multi node Pre-commit checks #5106: Pull request #1553 opened by blueswhen
35s fix_ctrlc
fix_ctrlc
35s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5105: Pull request #1549 synchronize by hiworldwzj
35s wzj_auto
wzj_auto
35s
Support request-level cache for hybrid sliding-window attention Pre-commit checks #5104: Pull request #1545 synchronize by shihaobai
41s bsh/hybrid-sliding-window-cache
bsh/hybrid-sliding-window-cache
41s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5103: Pull request #1549 synchronize by hiworldwzj
34s wzj_auto
wzj_auto
34s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5102: Pull request #1549 synchronize by hiworldwzj
43s wzj_auto
wzj_auto
43s
fix(cache): improve hybrid attention snapshot eviction Pre-commit checks #5101: Pull request #1551 opened by sufubao
38s sufubao:hybrid-cache-eviction
sufubao:hybrid-cache-eviction
38s
fix(cache): improve hybrid attention snapshot eviction Pre-commit checks #5100: Pull request #1550 opened by sufubao
38s sufubao:codex/hybrid-cache-eviction
sufubao:codex/hybrid-cache-eviction
38s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5099: Pull request #1549 synchronize by hiworldwzj
33s wzj_auto
wzj_auto
33s
feat(autotune): separate general and decode attention warmup Pre-commit checks #5098: Pull request #1549 synchronize by hiworldwzj
48s wzj_auto
wzj_auto
48s