VQV Signal

ROBOTS & HARDWARE WATCH TECHNICAL

Team reports Claude-written megakernels decode up to 1.77× faster than vLLM and SGLang

According to a post on X by @xingyudang, his team had Claude write a separate megakernel, a single GPU kernel that runs the entire decode loop, for each of 8 open models ranging from 8B to 594B parameters. The post reports decoding up to 1.77× faster than vLLM and SGLang, and 2.05× with lossless model-specific tricks. The author argues that one-size-fits-all inference engines are on the way out. These figures come from the post itself and the snippet is truncated, so the full method is not visible here.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-20T05:50:00+00:00 Detected 2026-11-20T20:04:04+00:00
View original source

According to a post on X by @xingyudang, his team had Claude write a separate megakernel, a single GPU kernel that runs the entire decode loop, for each of 8 open models ranging from 8B to 594B parameters. The post reports decoding up to 1.77× faster than vLLM and SGLang, and 2.05× with lossless model-specific tricks. The author argues that one-size-fits-all inference engines are on the way out. These figures come from the post itself and the snippet is truncated, so the full method is not visible here.

AI-assisted summary based on the listed source.

@xingyudang said his team had Claude write a separate megakernel, one GPU kernel that runs the entire decode loop, for each of 8 open models from 8B to 594B parameters. He reported up to 1.77× faster decoding than vLLM and SGLang, and 2.05× with lossless model-specific tricks, arguing that one-size-fits-all...

If coding agents can reliably hand-tune kernels for individual models, teams running open-weight models could gain speed without depending only on general-purpose inference engines. Builders and inference providers would need independent benchmarks to see whether these gains hold up and whether the approach extends beyond the eight models named.

Hardware and robotics watchers may want to track whether this becomes a product, benchmark, or deployment signal.

Signal Strength 95% Technical label WATCH Public Interest 39 Category ROBOTS & HARDWARE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 60 Practical Impact Score 0 Novelty Interest Score 70 Consequence Score 18 Curiosity Score 16 Shareability Score 54

VQV surfaced this signal because it is recent, relevant to LLM Inference, connected to Scobleizer News Pulse (X).