Searcharxiv⌕ Search

arXiv subjects

Kesavan Ramakrishnan

Publications and source records attributed to Kesavan Ramakrishnan.

2 recordsLinked to original sources

Together Compiler: Continual Compilation for AI Inference

Today's AI workloads are rapidly changing: new models are released more often, model architectures are increasingly diverse, and traffic distributions change frequently. The challenge we face at Together AI is continual optimization for these changing workloads. Compiling a deployment into an optimized forward pass is a challenge that is well-suited for agent hill-climbing. Existing systems struggle with continual compilation due to a tradeoff between measurement throughput and fidelity. Many systems use agents to optimize individual kernels from the inference forward pass using offline benchmarks, but timings are low-fidelity because of data-dependent behavior in primitives like mixture-of-experts (MoE). On the other hand, systems use agents to directly optimize end-to-end engines but suffer from slow engine launch times. To address these challenges, we build Together Compiler (TKCC), the first truly continual agent loop designed for AI inference optimization. To address the throughput-fidelity tradeoff, we propose: (1) a Tiered Persistent Engine that decouples engine launch overheads from forward pass computation; (2) a cost model to select the parallelism configurations that seed the optimization process. We also conduct extensive ablations on agent context management and present our insights on deploying TKCC in production. TKCC outperforms highly-optimized hand-written Megakernels on the Llama 1B workhorse workload by up to 1.7x and the best open source engines on the latest frontier models (Kimi K3, GLM 5.3, MiniMax M3.1 Flash, DeepSeek v4.1 Flash) across hardware platforms by up to 2.6x higher TPS on the InferenceX benchmark. TKCC also sets the state-of-the-art performance at batch size 1, with 1111 TPS on M3.1 Flash and 1205 TPS on DeepSeek v4.1 Flash. Finally, TKCC generalizes beyond frontier language model inference. TKCC serves trillions of tokens across our production fleet.

cs.AI↗

SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization

Large language models (LLMs) have shown progress in GPU kernel performance engineering using inefficient search-based methods that optimize around runtime. Any existing approach lacks a key characteristic that human performance engineers rely on for near-optimal utilization -- hardware-awareness. By leveraging the workload's specific memory access patterns, architecture specifications, filtered profiling logs, and reflections on historical performance, we can make software-level optimizations that are tailored to the underlying hardware. SwizzlePerf automatically generates spatial optimizations for GPU kernels on disaggregated architectures by giving LLMs explicit hardware-awareness. For a GEMM kernel, SwizzlePerf takes less than 5 minutes to generate the same hardware-specific optimal swizzling pattern that took expert performance engineers 2 weeks to find. On a suite of 10 diverse ML and Science kernels, SwizzlePerf can generate swizzling patterns for 9 of the kernels that achieve up to a 2.06x speedup and 70% improvement in L2 hit rate. This work is the first of many steps toward systematically creating hardware-aware LLM performance engineering agents.

cs.DC↗