inference/research
verifiedmedium · 0.70updated 2026-10-04

vllm-gfx906-mobydick: maintained gfx906 fork of vLLM

repo

Fields

id
sources/comm-vllm-gfx906-mobydick-repo
URL
https://github.com/ai-infos/vllm-gfx906-mobydick
Publisher
GitHub (ai-infos)
Kind
repo
Accessed
2026-10-04
notes
Successor to the archived nlzy/vllm-gfx906. Carries the gfx906 Triton Flash Attention kernels and GPTQ/AWQ/MoE/exllama support.

Notes

Successor to the archived nlzy/vllm-gfx906. Carries the gfx906 Triton Flash Attention kernels and GPTQ/AWQ/MoE/exllama support.

Cross-references

This record references no other records.