Hugging Face Trending Papers
The paper investigates how various non‑quantization factors—such as engine changes, server restarts, batching differences, and kernel selection—affect the performance of quantized language models compared to their BF16 baselines. Using 2,400 public decisions from Cloudflare’s Clef‑flash (9B) and Clef (27B) models on an NVIDIA GB10, the authors quantify the noise introduced by each factor and isolate the true impact of different quantization schemes (8‑bit, FP8, Q4_K_M, NVFP4). They find that non‑quantization sources contribute up to 0.92% of decision changes, while 4‑bit quantization can alter accuracy by up to 0.95 points, and they provide code, recipes, and detailed per‑record outputs for reproducibility.
arXiv:2608.23816v1 Announce Type: new
Abstract: Quantized fine-tuning (QLoRA) saves memory but not time. It dequantizes every 4-bit weight on the fly, so it trains more slowly than fp16 LoRA. We pres...
By Md Romyull Islam
The study evaluates the portability of INT8 post‑training quantization across seven hardware platforms, including CPUs, GPUs, and vendor NPUs, by keeping the ONNX model and quantization scales constant. It finds that INT8 performance and output consistency vary significantly: CPU dot‑product instructions determine speedup, identical INT8 outputs only occur when integer kernels match, and vendor NPUs require their own quantization pipelines. The authors also show that edge‑NPU latency is dominated by data transfer rather than compute and provide scripts and reports for reproducibility.
By Yuyeong Shin
arXiv:2607. 11368v1 Announce Type: cross Abstract: Reported serving speedups from quantized kernels typically bundle the weight format, the kernel, and the inference runtime into one number.
By Weijia Han, Lisha Qu
arXiv:2608. 13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable.
By Teng-Ruei Chen
Low-precision arithmetic can make reinforcement learning (RL) for large language models cheaper, but RL requires the sampler and the learner to agree. Several frameworks now run FP8 on both sides. We...
The paper presents an end‑to‑end MXFP8 reinforcement learning implementation on Blackwell GPUs, evaluating its benefits and limitations with Qwen3-8B and Qwen3-30B-A3B models. It finds that matching FP8 precision between sampler and learner improves consistency, that speed gains appear only for large micro‑batches, and that several weight‑synchronization correctness conditions can fail silently. The study also introduces seven explicit checks to detect such failures during training.
By Wengee Zhang
The paper investigates how prefix caching, a default optimization in open‑source LLM serving stacks, affects reproducibility when combined with weight quantization. Experiments on an eighty‑episode multi‑turn agentic tool‑use workload show that enabling the cache causes the agent’s trajectory to change in 36.2 % of episodes at 16‑bit precision and 75.0 % at 4‑bit precision, while disabling the cache yields perfectly reproducible runs. The study identifies specific cache‑related settings that drive run‑to‑run divergence and demonstrates that cached serving is deterministic only when the cache state is preserved, which is not the case in typical deployments.
By Aditi Patodiya
ScaleRLT introduces a hybrid learner log‑probability method that reconciles differences between dense and deferred rollout computations in looped language models like Ouro. By using a stop‑gradient replay of the rollout schedule, the approach achieves bit‑for‑bit reproducibility across FP32 and bf16 real‑weight cells while maintaining the same gradient accuracy as dense implementations. The technique boosts rollout throughput by up to 1.56× on a single GPU and significantly speeds up multi‑node GRPO updates, leading to substantial accuracy gains on GSM8K in short training runs.
By Dezhen Lu, Zixiang Ni, Runguo Li
arXiv:2605. 06675v2 Announce Type: replace Abstract: Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving.
By Fei Zuo, Zikang Zhou, Hao Cong, Xiaoyan Xi, Ho Fai Leung
A team serving a 9B-20B open-weight language model on vLLM or SGLang must choose a quantization recipe, and needs two numbers: the speedup over BF16 and the accuracy given up. We assemble every public...
arXiv:2603. 09555v2 Announce Type: replace-cross Abstract: High-throughput Mamba-2 inference is usually tied to fused CUDA and Triton kernels, limiting portability across accelerator backends.
By Cosmo Santoni, Anmol Thapar
arXiv:2609.07901v1 Announce Type: new
Abstract: Weight quantization largely determines the economics of serving open-weight LLMs. Its costs are usually assessed with capability benchmarks, on which 4...
By Dachi Kurtskhalia