Logo
Explore Help
Register Sign In
TBNilles/qwen3.5-122B-A10B-on-spark
Watch 1
Star 0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
18 Commits 1 Branch 0 Tags
1d0f2e1af3c4953783af554a07110738bc891d6b
Commit Graph

2 Commits

Author SHA1 Message Date
ent 9b7be16bee int8 lm-head: output bf16 (match stock lm-head dtype) instead of fp32 — halves the logits buffer that was inflating vLLM's profiled activation reserve and shrinking the dense KV pool 2026-06-24 15:53:58 +10:00
ent 60bf1b7b02 qwen3.5-122B-A10B on DGX Spark: vLLM + DFlash + dense-bandwidth stack, one-shot installer 2026-06-24 13:02:35 +10:00
Powered by Gitea Version: 1.27.0+dev-308-g6f4027a6be Page: 16ms Template: 1ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API