markbaseengine

T

MarkBase Admin 5a94501f95 Add bf16 layer weight support for E4B model

- Add FloatWeights fields to E4BLayer (qProjFloat, kProjFloat, etc.)
- Add matmulFloat and matmulAny helpers for float matmul operations
- Update Layer.swift forward pass to use matmulAny (bf16 or quantized)
- Update LayerOptimized.swift and LayerBatch.swift for bf16 weights
- Modify Model.swift to load bf16 layer weights via fw() helper
- Add guards in LayerBatch.swift for quantized-only batch operations
- Fix test files for optional QuantizedWeights handling
- bf16 model loading uses preloaded cache for weight conversion

Tested: E4B bf16 model forward pass works (5.5 tok/s, no NaN/Inf)
Tested: 4-bit models still work correctly after changes

2026-07-05 13:36:24 +08:00

.gitea/workflows

v2: Fix build conflict and unit tests

2026-07-05 13:31:45 +08:00

Scripts

v2: Initial clean branch with unit tests + CI/CD pipeline

2026-07-05 13:29:25 +08:00

Sources

Add bf16 layer weight support for E4B model

2026-07-05 13:36:24 +08:00

Tests

v2: Fix build conflict and unit tests