ShareGPT
PulseAugur coverage of ShareGPT — every cluster mentioning ShareGPT across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Astrolabe system optimizes LLM serving with randomized prediction-guided scheduling
Researchers have developed Astrolabe, a novel scheduling system designed to optimize the serving of large language models (LLMs). This system employs a randomized prediction-guided approach to balance load across multip…
-
Speculative Decoding Performance Varies Wildly Across Models
Speculative decoding, a technique designed to speed up AI model inference, has been found to degrade performance significantly under certain conditions. When tested on Llama-3-70B, the technique became a "tax" by batch …
-
qKnow Agent Platform Pro v3.1.1 streamlines AI knowledge ingestion
qKnow Agent Platform Pro has released version 3.1.1, focusing on improving the efficiency of knowledge ingestion for AI agents. The update addresses common bottlenecks such as handling semi-structured data like JSON and…
-
Sangam system optimizes serving for diffusion language models
Researchers have developed Sangam, a new serving system designed to efficiently handle diffusion language models (dLLMs). Unlike traditional autoregressive models, dLLMs generate text iteratively and have bidirectional …
-
AgentTrove dataset enables streaming analysis of 1.7M agent traces
This tutorial introduces AgentTrove, a large open-source dataset of agentic interaction traces, accessible via streaming to avoid full downloads. It details methods for inspecting conversation schemas, normalizing turns…
-
New memory paging technique boosts hybrid LLM inference efficiency
Researchers have developed a new memory management technique called Asymmetric Virtual Memory Paging (AVMP) to improve the efficiency of hybrid language models. These models combine Transformer layers with State Space M…
-
AgentHER framework boosts LLM agent training with failed trajectory relabeling
Researchers have developed AgentHER, a new framework designed to improve the training of LLM agents by repurposing failed trajectories. The system adapts Hindsight Experience Replay to natural language, identifying alte…