Amazing!
Curious, what happens to performance? I assume you still pay the same performance price for longer context, even if you can now fit it in memory.
replies(1):
I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising:
- K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality
This means you can run LLMs with 2-3× longer context on the same Mac. Memory usage scales with sequence length, so savings compound as context grows.
Implementation was straightforward: 1. Added --kvq-key and --kvq-val flags to llama.cpp 2. Applied existing quantization logic separately to K and V tensors 3. Validated with perplexity metrics across context lengths 4. Used Metal for acceleration (with -mlong-calls flag to avoid vectorization issues)
Benchmarked on an M4 MacBook Pro running TinyLlama with 8K context windows. Compatible with Metal/MPS and optimized for Apple Silicon.
It doesn't make sense to me though, I haven't looked into how it works inside but I would've thought it would pack vectors and then do 4-8b simd on all of them at once, but it really seems like it's not packing em.