Zijie Tian 2771312565 [docs] Add sparse prefill integration plan from int-minference analysis ...

Consolidated analysis from int-minference-1/2/3 branches into a unified
integration plan for MInference, XAttention, and FlexPrefill strategies.

Key design decisions:
- Backward compatible: Keep existing SparsePolicy interface
- Unified BlockMask intermediate representation for new strategies
- XAttention/FlexPrefill use block_sparse_attn_func kernel
- MInference can optionally use block_sparse_attn (Phase 4)

Five-phase implementation plan:
1. BlockMask + block_sparse_attn wrapper
2. XAttention implementation
3. FlexPrefill implementation
4. Optional MInference refactoring
5. Integration and testing

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-10 23:33:09 +08:00

..

architecture_guide.md

[claudesquad] update from 'lw-offload-2' on 08 Jan 26 21:19 CST

2026-01-08 21:19:38 +08:00

cuda_graph_offload_guide.md

[claudesquad] update from 'fix-bug-2' on 09 Jan 26 16:10 CST

2026-01-09 16:10:28 +08:00

debugging_guide.md

[claudesquad] update from 'lw-offload-2' on 08 Jan 26 21:19 CST

2026-01-08 21:19:38 +08:00

gpu_only_performance_issue.md

[claudesquad] update from 'int-minference-1' on 08 Jan 26 23:22 CST

2026-01-08 23:22:38 +08:00

layerwise_offload_memory_analysis.md

[claudesquad] update from 'lw-offload-2' on 08 Jan 26 21:19 CST

2026-01-08 21:19:38 +08:00

multi_model_support.md

[claudesquad] update from 'add-llama-1' on 10 Jan 26 21:14 CST

2026-01-10 21:14:32 +08:00

sparse_attention_guide.md

[claudesquad] update from 'lw-offload-2' on 08 Jan 26 21:19 CST

2026-01-08 21:19:38 +08:00

sparse_offload_integration.md

[claudesquad] update from 'int-minference-1' on 08 Jan 26 23:42 CST

2026-01-08 23:42:30 +08:00

sparse_prefill_integration_plan.md

[docs] Add sparse prefill integration plan from int-minference analysis

2026-01-10 23:33:09 +08:00