Gunjan Dhanuka — Learning Notes
Search
Search
Dark mode
Light mode
Reader mode
Explorer
mqa
3 items with this tag.
Sep 10, 2026
GQA / MQA (Grouped & Multi-Query Attention)
attention
kv-cache
gqa
mqa
inference
uptraining
llama
long-context
Sep 10, 2026
Learn: MQA → GQA → MLA (Shrinking the KV Cache)
attention
kv-cache
mqa
gqa
mla
deepseek
inference
long-context
transformers
Sep 02, 2026
KV Cache
gpu
kv-cache
inference
serving
decode
memory-bound
gqa
mqa
llm-systems