torch.profiler
PulseAugur coverage of torch.profiler — every cluster mentioning torch.profiler across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Hugging Face details async processing and PyTorch profiling
This cluster covers two technical blog posts from Hugging Face, shared via Mastodon. The first post, "Continuous Async," delves into the intricacies of asynchronous processing within continuous batching for AI models. T…
-
Hugging Face details async processing and PyTorch profiling
Hugging Face has published two technical blog posts detailing advancements in AI development. The first post, "Continuous Async in Batched Processing," explores methods for enhancing asynchronous operations within batch…
-
Hugging Face details async processing and PyTorch profiling
Hugging Face has published two blog posts detailing technical aspects of AI development. The first post, "Continuous Async," explores asynchronous processing in batched operations, while the second, "PyTorch Profiler," …
-
IBM releases open-source multilingual embedding model with 32K context
IBM has released Granite Embedding Multilingual R2, an open-source embedding model under the Apache 2.0 license. This model supports a 32K context window and claims to achieve top-tier search quality with less than 100 …
-
IBM releases open-source multilingual embedding model with 32K context
IBM has released Granite Embedding Multilingual R2, an open-source embedding model under the Apache 2.0 license. This model supports a 32K context window and aims to achieve top-tier search quality with fewer than 100 m…
-
Hugging Face details Holotron-12B agent and PyTorch profiling guide
Hugging Face has released information on two distinct AI-related topics. The first is Holotron-12B, described as a high-throughput computer usage agent. The second topic covered is an introductory guide to torch.profile…
-
Hugging Face Spotlights AI Tools: Holotron-12B, olmo-eval, and PyTorch Profiler
Hugging Face is highlighting several AI-related projects and tools. This includes Holotron-12B, an agent designed for high-throughput computing, and olmo-eval, an evaluation workbench for model development loops from th…
-
LiDAR detector latency cut by optimizing voxelization, not backbone
Researchers profiling a LiDAR object detector discovered that the voxelization and scatter-to-pillars steps, not the 3D convolutional backbone, consumed approximately 40% of the per-frame latency. By moving the voxeliza…
-
Hugging Face Blog: PyTorch Profiler Guide for LLM Optimization
Hugging Face has released the first part of a blog series detailing how to use PyTorch's torch.profiler tool. This guide aims to demystify the process of profiling for developers, starting with a basic matrix multiplica…