ENTITY
SpectralQuant
SpectralQuant
PulseAugur coverage of SpectralQuant — every cluster mentioning SpectralQuant across labs, papers, and developer communities, ranked by signal.
Total · 30d
1
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
1 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
New methods target LLM KV cache compression for efficiency
Researchers are developing advanced techniques to compress the Key-Value (KV) cache in Large Language Models (LLMs), a major contributor to memory costs during inference. New methods like JoLT and FlashJoLT utilize tens…
-
SpectralQuant method recovers 96.5% of BF16 performance gap in Qwen3.5 model
Spectral Labs has developed a new quantization method called SpectralQuant, which aims to improve the performance of smaller model footprints. Their initial release, a Qwen3.5 0.8B model quantized to Q4_K_M, reportedly …