[Serving] PagedKVCache Quantization #2663
Open
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
KV Cache might be a burden under tight memory constraints, and cache quantization can reduce its memory requirement by roughly 75% (float16 -> int3 KV cache). As a result, this PR intends to introduce initial support for KV Cache quantization, introducing two new quant schemes (
q3f16kv
andq4f16kv
).On Llama-3 (
context_window_size = 8192
) kv cache memory usage:q4f16_1
: float16 kv cache)q4f16kv
: int4 kv cache)q3f16kv
: int3 kv cache)Depends on: apache/tvm#17159
cc @MasterJH5574 @tqchen