howtospark
Training

MLA / GQA (architectural KV)

KV compressionReference

Grouped-query (GQA/MQA) and low-rank latent KV (DeepSeek MLA) baked into the architecture.

Relieves
KV cacheBandwidth
Targets
KV cache · Structure
Format
Shared / low-rank KV heads
Granularity
Head grouping / latent KV
Lifecycle
Training-time · needs gradients
Calibration
Full corpus
Compression
Large KV reduction
Quality
Near-baseline (a design choice, not post-hoc)
Hardware
None — architectural
Runtimes
vLLMTensorRT-LLMSGLang

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