Searcharxiv⌕ Search

arXiv subjects

Byungsoo Oh

Publications and source records attributed to Byungsoo Oh.

6 recordsLinked to original sources

MegaOps: A Kernel Overlapping Framework with PyTorch-like Modularity and Megakernel Performance

Modern ML frameworks execute models using the kernel-per-operator paradigm, which runs each operator as a separate GPU kernel. This paradigm is modular, since developers can compose various kernel implementations and profile each kernel in isolation. However, this paradigm enforces dependencies at the granularity of entire kernels, which places a barrier between dependent kernels. These barriers cause streaming multiprocessors to idle, serialize computation and communication, and prevent a kernel from prefetching its weights while the preceding kernel runs. Megakernels remove kernel barriers by fusing the operators of an entire layer or model into a single kernel, but they give up the modularity of the kernel-per-operator paradigm. In this work, we ask whether a kernel-per-operator ML framework can perform on par with megakernels. Our key insight is that removing kernel barriers does not require fusing kernels. We develop MegaOps, a framework that launches dependent kernels on separate CUDA streams and enforces each dependency on individual tiles of the intermediate tensor that the producer kernel writes and the consumer kernel reads. Since kernels synchronize on data tiles instead of on each other's thread blocks, any two kernels that adopt the same data tiling can be composed without modifying either kernel. We evaluate MegaOps on dense Llama3 and Qwen3 models on single H100, A100, and L40 GPUs and on multi-GPU servers with 4$\times$A100 and 8$\times$H100. Our MegaOps framework matches the throughput of hand-tuned ThunderKittens megakernels, and achieves 1.09$\times$-1.10$\times$ the decode throughput and 0.98$\times$-1.10$\times$ the prefill throughput of the best-performing baseline, while reusing existing Triton, cuBLAS, and cuDNN kernels.

cs.DC↗

CCL-Bench 1.0: A Trace-Based Benchmark for LLM Infrastructure

Evaluative claims about LLM infrastructure -- ``workload X is fastest on hardware Y with software Z'' -- depend on a complex configuration space spanning hardware accelerators, interconnect bandwidth, software frameworks, parallelism plans, and communication libraries. Current infrastructure evaluation benchmarks publish a small set of end-to-end numbers that do not explain why one configuration outperforms another. We present CCL-Bench, a trace-based benchmark that addresses the limitations of existing benchmarks by recording reusable evidence for every ML workload. Each contributed data point in CCL-Bench packages an execution trace, a YAML workload card, and the launch scripts. We have developed a community-extensible toolkit to compute fine-grained compute, memory, and communication efficiency metrics from this evidence. Using CCL-Bench, we surface three claims that summary-statistic benchmarks cannot support: (i) higher compute-communication overlap can coincide with longer training step time and reveal inefficient parallelization choices, (ii) doubling TPU interconnect bandwidth yields a much higher end-to-end improvement in step time than doubling GPU interconnect bandwidth on small and medium workloads, and (iii) the best-tuned configuration on one training framework can run up to 3$\times$ slower than the best-tuned configuration on a peer framework on identical hardware.

cs.DC↗

Eliminating Hidden Serialization in Multi-Node Megakernel Communication

Recent megakernel designs for Mixture-of-Experts (MoE) inference fuse expert computation with fine-grained, GPU-initiated communication into a single persistent GPU kernel, and outperform collective-based MoE on a single node by overlapping data transfer with compute at tile granularity. This benefit does not carry over cleanly to multi-node inference, where experts span many nodes connected by an RDMA fabric. Communication-bound MoE models regress by up to $10\times$ on 8 nodes, and the regression worsens with node count. We trace this regression to hidden serialization in proxy-based RDMA transports. The ordering requirement between each tile transfer and its completion signal forces a fence that drains the NIC pipeline, and its cost grows with the number of concurrent transfers. As a result, models whose per-expert compute is too small to absorb this inflated network latency expose communication on the critical path. We present \emph{Perseus}, which eliminates this serialization through two techniques. \emph{Decoupled signaling} batches fences at per-destination granularity, reducing fence count by $8\times$. \emph{NIC-side ordering} replaces proxy stalls with hardware fence flags, so the proxy never blocks. On proxy-based transports, Perseus achieves up to 10.3$\times$ end-to-end speedup. Perseus on IBRC matches or exceeds IBGDA GPU-direct by up to 1.2$\times$, which shows that serialization, rather than the choice between proxy-based and GPU-direct transport, is what bounds multi-node megakernel performance.

cs.DC↗

TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents

In RL post-training of LLM agents, calls to external tools take several seconds or even minutes, leaving allocated GPUs idle and inflating post-training time and cost. While many tool invocations repeat across parallel rollouts and could in principle be cached, naively caching their outputs for reuse is incorrect since tool outputs depend on the environment state induced by prior agent interactions. We present TVCACHE, a stateful tool-value cache for LLM agent post-training. TVCACHE maintains a tree of observed tool-call sequences and performs longest-prefix matching for cache lookups: a hit occurs only when the agent's full tool history matches a previously executed sequence, guaranteeing identical environment state. On three diverse workloads-terminal-based tasks, SQL generation, and video understanding. TVCACHE achieves cache hit rates of up to 70% and reduces median tool call execution time by up to 6.9X, with no degradation in post-training reward accumulation.

cs.LG↗

FlashMoE: Fast Distributed MoE in a Single Kernel

The computational sparsity of Mixture-of-Experts (MoE) models enables sub-linear growth in compute cost as model size increases, thus offering a scalable path to training massive neural networks. However, existing implementations suffer from low GPU utilization, significant latency overhead, and a fundamental inability to leverage task locality, primarily due to CPU-managed scheduling, host-initiated communication, and frequent kernel launches. To overcome these limitations, we develop FlashMoE, a fully GPU-resident MoE operator that fuses expert computation and inter-GPU communication into a single persistent GPU kernel. FlashMoE enables fine-grained pipelining of dispatch, compute, and combine phases, eliminating launch overheads and reducing idle gaps. Unlike existing work, FlashMoE eliminates bulk-synchronous collectives for one-sided, device-initiated, inter-GPU (R)DMA transfers, thereby unlocking payload efficiency by eliminating bloated or redundant network payloads in sparsely activated layers. When evaluated on an 8-H100 GPU node with MoE models comprising up to 128 experts and 16K token sequences, FlashMoE achieves up to 9x higher GPU utilization, 6x lower latency, 5.7x higher throughput, and 4x better overlap efficiency compared to state-of-the-art baselines, despite using FP32, whereas the baselines use FP16. FlashMoE shows that principled GPU kernel-hardware co-design is key to unlocking the performance ceiling of large-scale distributed ML. We provide code at https://github.com/osayamenja/FlashMoE.

cs.DC↗

DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation

Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. But it is also vulnerable to some small perturbation called an adversarial attack. This is a problem combined with the safety of artificial intelligence, which has recently been studied a lot. These attacks have shown that they can fool models of image classification, semantic segmentation, and object detection. We point out this attack can be protected by denoise autoencoder, which is used for denoising the perturbation and restoring the original images. We experiment with various noise distributions and verify the effect of denoise autoencoder against adversarial attack in semantic segmentation.

cs.CV↗