AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch

Ziyang Zhang, Xinheng Ding, Jiayi Yuan, Rixin Liu, Huizi Mao, Jiarong Xing, Zirui Liu

ICML 2026 · Reinforcement learning › RL from feedback · approach: RL for LLM reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Tree-Based Invariant Kernels on top of BIO (ablation)vLLM Qwen3-8B · AIME24 across TP and BScount of unique outputs: 7.87 -> 1Improved
add TBIK on top of BIO (ablation)vLLM Llama-3.1-8B-Instruct · AMC23max probability divergence (x1e-3): 21.06 -> 0Improved
add batch-invariant operations only (ablation)vLLM BF16 · AIME24/AMC23 across TP and BScount of unique outputs: 12.00 -> 7.87 (Qwen3-8B AIME24)Mixed
add BIO only (ablation)vLLM Llama-3.1-8B-Instruct · AIME24max probability divergence (x1e-3): 26.48 -> 27.54Hurt
add TBIK to vLLM and FSDP in RLGRPO Qwen3-1.7B · GSM8KPass@1: 0.60 -> 0.73Improved
add TBIK to vLLM and FSDP in RLGRPO Qwen3-1.7B · GSM8KKL between rollout and training enginesImproved
add BIO only in RL (ablation)GRPO Qwen3-1.7B · GSM8KPass@1: 0.60 -> 0.68Improved
add TBIK on top of BIO (ablation)SGLang Qwen3-8B · latency in/out 4096/4096end-to-end latency (s): 125.64 -> 130.36Hurt
use tree-based MatMul kernel instead of cuBLAS at large M (ablation)Tree-Based MatMul · BF16 kernel throughputTFLOPS: 190 -> 120 TFLOPSHurt
use FP32 tree-based MatMul instead of cuBLAS (ablation)Tree-Based MatMul · FP32 kernel throughputTFLOPSNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy