repoGitHubTrust 82 · PrimaryPublished yesterdayLive · 4h ago
SemiAnalysisAI/InferenceX
Open Source Continuous Inference Benchmark Research Platform — Kimi K2.7-Code, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Covers
newsOpenAI and Broadcom unveil LLM-optimized inference chipnewsIs it agentic enough? Benchmarking open models on your own toolingnewsHardware startup unveils inference acceleratornewsGLM-5.2: Built for Long-Horizon Tasksnews[Benchmark] Kimi K2.7 Code Q3 on Mac Studio M3 Ultra + RTX PRO 6000 over llama.cpp RPC: prefill improves, no changes in token generation/decode
Covers (incoming)
Related across the graph
newsGLM-5.2: Built for Long-Horizon TasksnewsOpenAI and Broadcom unveil LLM-optimized inference chipnews[Benchmark] Kimi K2.7 Code Q3 on Mac Studio M3 Ultra + RTX PRO 6000 over llama.cpp RPC: prefill improves, no changes in token generation/decodenewsHardware startup unveils inference acceleratornewsIs it agentic enough? Benchmarking open models on your own toolingnewsLocal benchmarks with a RTX 3090 - Qwen3.6 27b vs Ornith