AllFeed, trending, and board
FeedLatest news
TrendingOpen source and releases
BoardBlogs and showcases
TagsBrowse by topic

#inference-optimization

The latest AI and developer news about #inference-optimization, with the original source and a short summary.

AI Briefing

Privacy Policy Terms of Service Contact About Sources RSS Support us

Feed
Trending
Tags
Settings

Liquid AI Releases LFM2.5-VL-DSpark: An Experimental Draft Model for Faster Vision-Language Inference

·2026.09.24 23:00

Stanford and NVIDIA Release 'Contrastive Language Model' CLM with 9x Faster Inference

·2026.09.24 13:00

Meta Introduces Muse Realtime Avatar for Synchronized, Expressive Video Generation

·2026.09.23 09:00

'Cache-to-Cache' Framework Revealed for Direct KV-cache Communication Between LLMs Without Text

·2026.09.19 03:00

Video Rebirth Releases 8-Step LoRA 'HyperFlow' for MiniMax-H3

·2026.09.19 02:00

GLM-5.3-Flash Builds Inference Infrastructure on Cluster of Over 100,000 Chinese Accelerators, Achieving ~3x Performance Boost

·2026.09.18 09:00

Pinterest Unveils 3-Tower Engagement Co-Train Model: Achieves 1% CTR Lift and 30ms Latency

·2026.09.18 00:00

Apple Research Improves Discrete Flow Matching Trajectories with Energy Compass… 32% Perplexity Reduction vs. Teacher Model with 8-Step Inference

·2026.09.16 09:00

OpenWAM, an Open-Source Stack for Comparing Robot WAM Designs, Released

·1·2026.09.14 09:00

PickDeepSeek Releases V4.1-Flash: Replaces V4-Pro and Optimizes KV Cache

·3·2026.09.11 14:00

Building a Pinterest VLM Serving Stack Based on NVIDIA Dynamo

·3·2026.09.11 08:00

NVIDIA Dynamo Unveils Vision Encoder Disaggregated Serving Technology

·2026.09.11 07:00

VDN-H3: Hybrid Attention Model MiniMax H3 Generates Video Faster Than Real-Time (Note: H3 Model Unavailable in South Korea)

·2026.09.09 18:00

vLLM Publishes Performance Benchmarks for 5 Speculative Decoding Methods on AMD GPUs

·2026.09.07 18:00

LLMs Declare Their Own Attention Scope

·2026.09.05 15:00

3.85x Inference Speedup via Diffusion Draft Generation and AR Verification Based on GLM-OCR

·1·2026.09.03 18:00

Apple Silicon-only inference engine 'Lily' improves decoding speed by 35% over MLX-LM

·2026.09.02 09:00

llama.cpp Optimizes Metal for Qwen3.8

·2026.08.28 07:00

Qwen4Exp: N-gram Architecture Analysis

·4·2026.08.27 11:00

4-bit LLMs Surpass Original Model Performance

·1·2026.08.25 20:00

Weekly AI Papers: Agent RL and Inference Optimization

·2026.08.24 06:00

Unsloth Dynamic 3.0 GGUFs

·2026.08.20 03:00

vLLM Bottleneck Diagnostic Tool 'Profile' Released

·1·2026.08.19 05:00

Status Update on Low-Bit (1-bit/Ternary) Models and Inference Optimization

·2026.08.19 03:00

1
2
3
4
5
Next

1
2
3
4
5
6
7
Next

#inference-optimization | AI Briefing