michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tune prefill batching across Qwen profiles

Browse Source
This commit is contained in:
Mikei386
2026-09-15 16:57:53 +02:00
parent 78055996f5
commit b48fcc63d3
5 changed files with 37 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+4 -4
View File
@@ -22,20 +22,20 @@ UNCENSORED_PROJECTOR_FILE=qwen3.8-27b-abliterated/mmproj-Qwen3.8-27B-ABLITERATED
VISION_PROJECTOR_FILE=qwen/mmproj-BF16.gguf
FAST_CONTEXT=76800
FAST_BATCH_SIZE=64
FAST_UBATCH_SIZE=32
FAST_BATCH_SIZE=2048
FAST_UBATCH_SIZE=64
MEDIUM_CONTEXT=160000
MEDIUM_BATCH_SIZE=2048
MEDIUM_UBATCH_SIZE=512
LARGE_CONTEXT=192000
LARGE_BATCH_SIZE=2048
LARGE_UBATCH_SIZE=128
LARGE_UBATCH_SIZE=256
ULTRA_CONTEXT=262144
ULTRA_BATCH_SIZE=2048
ULTRA_UBATCH_SIZE=128
UNCENSORED_CONTEXT=80000
UNCENSORED_BATCH_SIZE=2048
UNCENSORED_UBATCH_SIZE=128
UNCENSORED_UBATCH_SIZE=256
FAST_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
MEDIUM_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
MEDIUM_TENSOR_SPLIT=85,15