Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

AEON-7/vllm-ultimate-dgx-spark

AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on MRv2, Triton NVFP4-KV (NHD-safe), NVFP4_AWQ, torch 2.13 + FlashInfer 0.6.16 trio, NCCL 2.30.7, TP=2-ready. One image serves the whole AEON fleet.

Owner
AEON-7 (personal account)
Stars
Stars: 149
Forks
Forks: 16
Language
Python
License
None
Created
2026
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by AEON-7

All 3 repos by AEON-7

Nearby in Python

All Python repos