cd/entity/Gemma 4 MTP· home› entities› Gemma 4 MTP
grep -l @gemma 4 mtp /news/*.json | wc -l → 1

Gemma 4 MTP

mentions 1 type Person feed RSS

// recent coverage 1 mentions

09:26
2026-09-07
vllm.ai
large-language-models

Speculative Decoding in vLLM on AMD GPUs

AMD's experiments with speculative decoding in vLLM on AMD Instinct MI300X and MI355X GPUs using the ROCm platform show that output-token throughput gains vary by drafting method, proposal length, mod…

// co-occurs with top 7 entities
AMD 1 vLLM 1 AMD Instinct MI300X 1 AMD Instinct MI355X 1 ROCm 1 EAGLE-3 1 DFlash 1
// topics top 3 topics
large language models 1 ai infrastructure 1 ai research 1