Together Compiler: Continual Compilation for AI Inference
cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/NVIDIA/TensorRT-LLM
Terminology
Sources
- Chronos-2: From Univariate to Universal Forecasting
- Generating Long Sequences with Sparse Transformers
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
- DeepSeek-V3 Technical Report
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- GLM-5: from Vibe Coding to Agentic Engineering
- Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators
- A multi-scale loss formulation for learning a probabilistic model with proper score optimisation
- SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
- Speculative Decoding: Performance or Illusion?
- MoBA: Mixture of Block Attention for Long-Context LLMs
- Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
- OLMoE: Open Mixture-of-Experts Language Models
- KernelBench: Can LLMs Write Efficient GPU Kernels?
- Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents