(WIP) Optimizing NVFP4 Grouped GEMM on Blackwell
238μs to 20μs using tcgen05 MMA, TMA async loads, cluster multicast, etc.
4 min
Flushable SSTables in Pebble
~60% performance improvement when ingested SSTs overlap with the memtable
11 min
Enforcing Robust Type Safety with ESLint
Surfacing ~250 type inconsistencies in Linear's type definitions
6 min
Shipping Linear Drafts
Making drafts a first-class entity throughout Linear
10 min
Concurrent manual compactions
Segmenting key space and parallelizing execution, 30% perf improvement
11 min