[Docs] update attribution to reflect EDEN foundation (#41666)

Signed-off-by: amitport <1131991+amitport@users.noreply.github.com>
This commit is contained in:
Amit Portnoy
2026-05-18 11:22:56 -07:00
committed by GitHub
parent 00e20e76f7
commit ce88f01c9a
2 changed files with 30 additions and 19 deletions
@@ -48,19 +48,25 @@ class TurboQuantConfig:
Applies Hadamard rotation followed by per-coordinate Lloyd-Max scalar
quantization for keys, and uniform quantization for values.
Historical note: this is the scalar case of the HIGGS quantization
method (Malinovskii et al., "Pushing the Limits of Large Language Model
Quantization via the Linearity Theorem", NAACL 2025; preprint
arXiv:2411.17525): rotation + optimized grid + optional re-normalization,
applied to KV cache compression. A first application of this approach to
KV-cache compression is in "Cache Me If You Must: Adaptive Key-Value
Quantization for Large Language Models" (Shutova et al., ICML 2025;
preprint arXiv:2501.19392). Both these references pre-date the
TurboQuant paper.
Historical note: the core algorithmic pattern implemented for key
quantization (Hadamard rotation followed by deterministic scalar
quantization and re-normalization) was originally established in DRIVE
(Vargaftik et al., NeurIPS 2021) and EDEN (Vargaftik et al., ICML
2022). This formulation is also mathematically equivalent to the
scalar case of the HIGGS quantization method (Malinovskii et al.,
"Pushing the Limits of Large Language Model Quantization via the
Linearity Theorem", NAACL 2025; preprint arXiv:2411.17525), which
subsequently generalized these concepts.
QJL is intentionally omitted — community consensus (5+ independent
groups) found it hurts attention quality by amplifying variance through
softmax.
A first application of this approach to KV-cache compression is in
"Cache Me If You Must: Adaptive Key-Value Quantization for Large
Language Models" (Shutova et al., ICML 2025; preprint
arXiv:2501.19392). All of these foundational and application
references pre-date the TurboQuant paper (Zandieh et al., ICLR 2026).
QJL is intentionally omitted: community consensus (5+ independent
groups) found it hurts attention quality by amplifying variance
through softmax.
Named presets (use via --kv-cache-dtype):
turboquant_k8v4: FP8 keys + 4-bit values, 2.6x, +1.17% PPL