Skip to content

Pull requests: ModelTC/LightLLM

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

refactor: generalize hybrid attention checkpoint management
#1559 opened Sep 9, 2026 by shihaobai Collaborator Loading…
fix(cache): reuse historical CPU tail pages for hybrid attention
#1558 opened Sep 9, 2026 by sufubao Collaborator Loading…
Add P/D metrics aggregation endpoint to PD master
#1556 opened Sep 9, 2026 by sufubao Collaborator Loading…
fix(sampling_params): reject out-of-range token ids at intake
#1554 opened Sep 9, 2026 by SuperMarioYL Contributor Loading…
fix: ctrl c for single and multi node
#1553 opened Sep 9, 2026 by blueswhen Collaborator Loading…
fix(cache): improve hybrid attention snapshot eviction
#1551 opened Sep 8, 2026 by sufubao Collaborator Loading…
feat: support DFlash2 for Qwen3.8
#1548 opened Sep 7, 2026 by Owleye4 Collaborator Loading…
Support request-level cache for hybrid sliding-window attention
#1545 opened Sep 4, 2026 by shihaobai Collaborator Loading…
feat(model): add neo chat model
#1536 opened Sep 2, 2026 by kingder Collaborator Loading…
perf: share vocab-parallel top-k logits for target and draft
#1534 opened Sep 1, 2026 by sufubao Collaborator Loading…
add eplb function
#1531 opened Sep 1, 2026 by blueswhen Collaborator Loading…
feat(pd): add node-authoritative Decode admission
#1529 opened Aug 31, 2026 by sufubao Collaborator Loading…
[draft] feat: support GLM-5.3-Flash inference
#1525 opened Aug 28, 2026 by sufubao Collaborator Loading…
feat: support multi-token KV cache pages
#1522 opened Aug 28, 2026 by hiworldwzj Collaborator Loading…
Optimize draft logits communication with sparse candidates
#1512 opened Aug 26, 2026 by hiworldwzj Collaborator Loading…
fix(dp): wait forward before gather_req
#1506 opened Aug 26, 2026 by WANDY666 Contributor Loading…
perf(pd): compact token forwarding packets
#1487 opened Aug 24, 2026 by WANDY666 Contributor Loading…
perf(pd): omit unused output logprob metadata
#1486 opened Aug 24, 2026 by WANDY666 Contributor Loading…
perf(pd): reduce disaggregated serving latency
#1481 opened Aug 24, 2026 by sufubao Collaborator Loading…
fix(pd): fail requests when assigned nodes disconnect
#1473 opened Aug 20, 2026 by sufubao Collaborator Loading…
fix: apply x_stride1 in the rmsnorm normalize pass
#1468 opened Aug 17, 2026 by truong-v Contributor Loading…
feat: imbalance statistics
#1466 opened Aug 14, 2026 by blueswhen Collaborator Loading…
ProTip! Updated in the last three days: updated:>2026-09-06.