Implement INT4 packing with group scales and a dequantizing matmul, and test it against FP32 with odd K and a partial group.
Two nibbles per byte and a scale per 128 weights sounds like bookkeeping. The grader checks the sign extension, the nibble order, what happens when K is odd or not a multiple of the group, and whether your error test has a bound or just a vibe.
Updated Oct 2026 · Worked answers on inference mechanisms, with calculations, implementation details, and follow-up questions.
Two nibbles per byte and a scale per 128 weights sounds like bookkeeping. The grader checks the sign extension, the nibble order, what happens when K is odd or not a multiple of the group, and whether your error test has a bound or just a vibe.
At batch 1 the step reads every weight once to produce one token per sequence, so arithmetic intensity sits near 1 FLOP per byte and the tensor cores idle.