#efficiency
- 14 Oct 2025 · Paper summary
Paper summary: QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
QeRL combines NVFP4 quantisation with LoRA for RL training of LLMs; beyond saving memory and speeding up rollouts, quantisation noise raises policy entropy and helps exploration. It enables RL on a 32B model with one H100.
- 26 Aug 2025 · Paper summary
Paper summary: InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
InternVL3.5 adds Cascade RL (offline then online RL), a Visual Resolution Router and decoupled vision/language deployment, reporting up to +16% reasoning and 4.05× faster inference than InternVL3.
- 8 Apr 2025 · Paper summary
Paper summary: SmolVLM: Redefining small and efficient multimodal models
SmolVLM is a family of compact vision-language models designed for on-device inference; the 256M model uses under 1GB of GPU memory and is reported to beat the 300× larger Idefics-80B.
- 7 Mar 2024 · Paper summary
Paper summary: GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
GaLore projects gradients into a low-rank subspace for the optimizer state while still updating all weights, cutting optimizer memory by up to 65.5% (82.5% in 8-bit) without LoRA's accuracy trade-off.
- 28 Feb 2024 · Paper summary
Paper summary: The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
BitNet b1.58 restricts every weight to −1, 0 or +1 (about 1.58 bits) and reports matching full-precision LLMs of the same size and data on perplexity and end tasks, at much lower cost.
- 20 Dec 2023 · Paper summary
Paper summary: LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Apple researchers run LLMs larger than the available DRAM by keeping weights in flash and loading only what is needed, with windowing and row–column bundling designed around how flash memory reads data.
- 10 Nov 2023 · Paper summary
Paper summary: LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
LCM-LoRA packages latent-consistency distillation as a LoRA that plugs into Stable Diffusion models and their fine-tunes to generate images in very few steps without extra training.
- 18 Oct 2023 · Paper summary
Paper summary: BitNet: Scaling 1-bit Transformers for Large Language Models
BitNet replaces nn.Linear with BitLinear and trains Transformers with 1-bit weights from scratch, reporting competitive perplexity with much lower memory and energy than FP16 or 8-bit baselines.