PulseAugur
EN
LIVE 16:16:34
ENTITY CUDA Graphs

CUDA Graphs

PulseAugur coverage of CUDA Graphs — every cluster mentioning CUDA Graphs across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
4
9 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
5 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

2 day(s) with sentiment data

RECENT · PAGE 1/1 · 9 TOTAL
  1. TOOL · CL_361903 ·

    Together AI pivots from megakernels to new compiler for faster AI inference

    Together AI has announced their new inference optimization framework, Together Compiler, which aims to improve AI model performance. Initially, the company developed "megakernels" that fused entire model forward passes …

  2. TOOL · CL_320027 ·

    llama.cpp fork boosts performance on legacy NVIDIA GPUs

    A developer has created a fork of the llama.cpp project to enhance performance on older NVIDIA GPUs, specifically targeting Kepler architecture and pre-Ampere models. This fork introduces support for CUDA Graphs and Win…

  3. TOOL · CL_316407 ·

    Gradium open-sources Phonon on-device TTS models

    Gradium has released Phonon, a family of on-device text-to-speech models available in 31M and 40M parameter sizes. The English-only Phonon 31m model, licensed under Apache 2.0, is a compact 64.5 MB and can generate spee…

  4. TOOL · CL_322467 ·

    DuoLM framework boosts recommendation speed with dual language models

    Researchers have introduced DuoLM, a novel framework designed to enhance the speed and efficiency of personalized recommendation systems using language models. DuoLM employs a two-model approach: a compact encoder that …

  5. TOOL · CL_275331 ·

    DynaFlow framework enhances ML parallelism with programmable operator scheduling

    Researchers have developed DynaFlow, a new framework designed to improve intra-device parallelism for machine learning inference and training. DynaFlow decouples the logical model definition from the physical execution …

  6. TOOL · CL_215165 ·

    ShardFlow framework achieves 28 TPS on Qwen2.5-7B using speculative decoding

    A developer has built ShardFlow, a distributed LLM inference framework that splits models across multiple machines and uses speculative decoding to mitigate WAN latency. Benchmarks on Qwen2.5-7B demonstrated a significa…

  7. TOOL · CL_181100 ·

    New WAM-Diff2 framework boosts autonomous driving VLA model efficiency

    Researchers have developed WAM-Diff2, a new framework designed to improve the efficiency of Vision-Language-Action (VLA) models for autonomous driving. This framework uses a hierarchical distillation strategy to convert…

  8. TOOL · CL_117583 ·

    HARD-KV framework boosts LLM inference speed by 2x

    Researchers have developed HARD-KV, a novel framework designed to optimize long-context Large Language Model (LLM) inference. This system addresses the conflict between head-adaptive compression algorithms, which offer …

  9. RESEARCH · CL_62734 ·

    AI inference latency limited by more than memory bandwidth, study finds

    A new paper reveals that the inference performance of physical AI systems, such as robots and autonomous vehicles, is not solely limited by memory bandwidth as previously assumed. The research demonstrates that while ba…