SemiAnalysis

@SemiAnalysis_

已收录 10 条帖子

#1

Video posted by SemiAnalysis (@SemiAnalysis_)

SemiAnalysis @SemiAnalysis_ · 19 小时前
#2

BREAKING NEWS🚨: @Inferact & Google submit their FIRST preliminary TPUv7 Kimi K3 2.8T Model Submission, and it is already delivering strong perf per TCO against GB200 NVL72, B3…

SemiAnalysis @SemiAnalysis_ · 1 天前
#3

BREAKING NEWS🚨: NVIDIA has just achieved 423 tok/s/user 🚀 on the 2.8T Parameter Kimi K3 model via a new upstream vLLM optimization. 1.68x Faster on the Same Hardware! This was don…

SemiAnalysis @SemiAnalysis_ · 1 天前
#4

GLM 5.3’s biggest leap came from post-training alone. “GLM 5.3 was built entirely by post-training the previous model. For me, that was a wake-up call.” “Post-training is far more…

SemiAnalysis @SemiAnalysis_ · 1 天前
#5

TOKENMAXXING: @vllm_project and @inferact achieve 1.3 BILLION tokens per $ of TCO (hyperscaler volume pricing) via disaggregated serving on AgentX. This result is 4x better than t…

SemiAnalysis @SemiAnalysis_ · 2 天前
#6

MEME: If GPT-7 is AGI, OpenAI could potentially ditch Broadcom entirely and bring everything in-house, as GPT-7 could be better than Broadcom at designing 224G SerDes, handling PD…

SemiAnalysis @SemiAnalysis_ · 2 天前
#7

The agent access war has started！ Meta's Muse recently hit #1 on the App Store. But soon Amazon blocked it. Jefferies then found a third of the US shopping and travel sites it tes…

SemiAnalysis @SemiAnalysis_ · 2 天前
#8

Photo posted by SemiAnalysis (@SemiAnalysis_)

SemiAnalysis @SemiAnalysis_ · 3 天前
#9

Sparse attention fixes memory bandwidth, not memory capacity. “The whole idea of HiCache is trying to offload KV cache from the HBM to a lower tier, higher capacity but lower band…

SemiAnalysis @SemiAnalysis_ · 3 天前