XenonFear128 commited on
Commit
0f11fda
·
verified ·
1 Parent(s): bbb8d6a

Upload docs/5090D-acceptance-checklist.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. docs/5090D-acceptance-checklist.md +14 -0
docs/5090D-acceptance-checklist.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # 5090D acceptance checklist
2
+
3
+ Run the k=2 v2 profile on a single RTX 5090D before publishing performance numbers.
4
+
5
+ - Use `context_length=262144` and test `261632` input tokens plus `56` output tokens.
6
+ - Keep main KV at NVFP4 and MTP draft KV at FP8 E4M3.
7
+ - Keep the validated FlashInfer workspace at 144 MiB; increase only if the backend reports a required buffer larger than this, then repeat the memory gate.
8
+ - Sample NVML memory at 20 ms or faster from process start through request completion.
9
+ - Require peak device usage at or below 32268 MiB (32 GiB minus 500 MiB).
10
+ - Require at least 500 MiB free relative to a 32 GiB device budget.
11
+ - Check prompt token count, cached tokens, all three retrieval facts, MTP acceptance, and decode throughput.
12
+ - If k=2 exceeds the memory gate, rerun the unchanged k=1 fallback before changing weight precision.
13
+
14
+ The current k=2 v2 evidence is from an RTX PRO 6000 and cannot substitute for this hardware check.