Skip to content

Verify long-context quality (KLD) for INT4 / rotation #69

Description

@geisten

Follow-up to #61 / #65.

Quality (mean KL vs FP32) was measured only at ~300 tokens; decode cost was measured out to kv_len ~3072 (where INT4 is net-faster). What's unverified is whether INT4 / INT4+ROT stays near-lossless at long context — accumulated quantization error over thousands of positions.

Task: extend tests/bench_kv_quality (or a variant) to teacher-force a long document (2–4k tokens) and report mean KL per mode at, say, the last 512 positions vs the first 512. Rotation is position-independent so quality should hold, but it's an assumption.

Impact: moderate — confirms (or refutes) that the "near-lossless" claim holds in the regime packed INT4 is actually for (long chats, RAG, agents).

Metadata

Metadata

Assignees

No one assigned

    Labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions