Runs on stock vLLM v0.34.0 (no b12x) on one DGX Spark β recipe and one gotcha
#16 opened about 22 hours ago
by
CTala
Will you make the same job for Qwen4.0 Flash?
#15 opened 4 days ago
by
moranilt
Byte indentical to local-inference-lab model
#14 opened 7 days ago
by
vvekthkr
DGX Spark: load OOM fixed with PYTORCH_ALLOC_CONF, plus results at 131K context
#13 opened 14 days ago
by
howellx
Running FP4-Local on 4 Γ V100 32 GB (Volta) with ReVolta
#12 opened 24 days ago
by
leoncca
Recipe for 4x RTX Pro 4000
#11 opened 24 days ago
by
jmig1109
Serving FP4-Local on SGLang (one RTX PRO 6000, PRs open for review)
π 1
1
#10 opened 27 days ago
by
AndreasBis
Please implement Thor Devkit deployment
π 2
#9 opened 27 days ago
by
the-z0rb
made my DGX Spark more valuable
#7 opened about 1 month ago
by
gmrxde
Merci !
#6 opened about 1 month ago
by
QuentinReytinas
Docker (WSL2)?
5
#5 opened about 1 month ago
by
evilperson068
Recipe for VLLM dev (no docker container), and Humaneval benchmark results vs RadixArk
π 11
2
#4 opened about 1 month ago
by
OverleapSecreted