Skip to content

[TRTLLM-16288][feat] Integrate sparse KV offload for DeepSeek-V4 Flash and GLM5.2 on KVCM2 - #21350

Open
cascade812 wants to merge 13 commits into
NVIDIA:mainfrom
cascade812:guiju/sparse-kv-offload
Open

[TRTLLM-16288][feat] Integrate sparse KV offload for DeepSeek-V4 Flash and GLM5.2 on KVCM2#21350
cascade812 wants to merge 13 commits into
NVIDIA:mainfrom
cascade812:guiju/sparse-kv-offload

[None][fix] Restore sparse indexer defaults and refine offload coverage

50e1e45
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Nov 3, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO