-
Notifications
You must be signed in to change notification settings - Fork 0
Pull requests: jagmarques/nexusquant
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
C6: Mixtral-8x7B manual per-layer GPU streaming (bypass accelerate)
#44
opened Jun 16, 2026 by
jagmarques
Owner
•
Draft
C6: Mixtral-8x7B T4x2 AQUA-iso paired PPL + NIAH kernel (v3, memory-fit)
#39
opened Jun 16, 2026 by
jagmarques
Owner
•
Draft
Qwen3-8B RULER/multi-needle NIAH for Hurwitz head-to-head
#34
opened Jun 15, 2026 by
jagmarques
Owner
•
Draft
iso-bpe E8 vs scalar KV quant on Mistral-7B (n=60); 24-cell baseline not a valid HQMQ comparison
#33
opened Jun 15, 2026 by
jagmarques
Owner
•
Draft
Add calibration-free engine_kv module for inference-engine integration (C15a)
#32
opened Jun 15, 2026 by
jagmarques
Owner
•
Draft
Discriminative diverse-text rescue test (Mistral-7B 4K, FP16-failing operating point, n=40)
#31
opened Jun 15, 2026 by
jagmarques
Owner
•
Draft
Kaggle T4x2 Mistral RULER multi-needle paired beneficial-quant kernel (4K, n>=50)
#25
opened Jun 14, 2026 by
jagmarques
Owner
•
Draft
ProTip!
What’s not been updated in a month: updated:<2026-05-17.