howtospark
Training

Token eviction (H2O, StreamingLLM)

KV compressionReference

Drop low-impact tokens from the KV cache to cap long-context memory.

Relieves
KV cache
Targets
KV cache
Format
Sparse KV (evict tokens)
Granularity
Per-token
Lifecycle
PTQ · no gradients
Calibration
No calibration
Compression
Bounded KV regardless of length
Quality
Task-dependent
Hardware
Runtime eviction support
Runtimes
SGLangvLLM

A worked Spark recipe for this method hasn't been written yet — it lives here as a reference point in the ontology.