-
Notifications
You must be signed in to change notification settings - Fork 346
Pull requests: ModelTC/LightLLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(quant): add triton fp8 w8a8 per-tensor quantization method
#1404
opened Jul 24, 2026 by
sufubao
Collaborator
Loading…
zero deepstack layers on slot when audio reuse
#1400
opened Jul 22, 2026 by
WANDY666
Contributor
Loading…
feat: interleave CPU KV cache pages across NUMA nodes
#1399
opened Jul 21, 2026 by
sufubao
Collaborator
Loading…
fix: reduce memory occupation and raise performance for multi-nodes
#1396
opened Jul 17, 2026 by
blueswhen
Collaborator
Loading…
fix: fix bugs in the ep v2 and mega moe for sm100
#1392
opened Jul 15, 2026 by
blueswhen
Collaborator
Loading…
feat: gc.freeze hot processes and disable gc during cudagraph capture
#1382
opened Jul 5, 2026 by
sufubao
Collaborator
Loading…
Support GLM-5.2 (glm_moe_dsa, DeepSeek-V3.2-style DSA MoE)
#1370
opened Jun 25, 2026 by
sufubao
Collaborator
Loading…
fix(sampling_params): validate token-id input types via a shared helper
#1365
opened Jun 19, 2026 by
SuperMarioYL
Contributor
Loading…
fix(moe): avoid cross-warp stale read in ep_scatter prefix sum
#1362
opened Jun 16, 2026 by
Anai-Guo
Loading…
test(sampling_params): repair broken test collection and add verify() coverage
#1350
opened Jun 13, 2026 by
SuperMarioYL
Contributor
Loading…
feat: add multi-platform support with ascend and maca
#1335
opened Jun 8, 2026 by
zhangts20
Collaborator
Loading…
feat: update disk cache params and benchmark_multiturn.py
#1333
opened Jun 8, 2026 by
blueswhen
Collaborator
Loading…
fix: replace pickle deserialization with RestrictedUnpickler in PD WebSocket endpoints (CVE-2026-26220)
#1306
opened May 11, 2026 by
nexadodigital
Loading…
Previous Next
ProTip!
Adding no:label will show everything without a label.