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

Synchronize repository with Athena deployment

Browse Source
This commit is contained in:
Mikei386
2026-09-13 20:01:36 +02:00
parent 040a2df48b
commit fce9900389
60 changed files with 2570 additions and 607 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/install.env.example
+5 -11
View File
@@ -18,7 +18,11 @@ NVIDIA_MIN_DRIVER_MAJOR=570
TEXT_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe
SECONDARY_GPU_DEVICES=GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
IMAGE_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe
FLUX_MODEL_DIR=/data/models/FLUX.2-klein-4B
# FLUX.2 Klein 9B is gated. Accept both BFL model licenses first, then store
# the Hugging Face token in this root-readable file (never in this config).
HF_TOKEN_FILE=/root/.cache/huggingface/token
FLUX_COMPONENT_DIR=/data/models/FLUX.2-klein-9B-components
FLUX_TRANSFORMER_DIR=/data/models/FLUX.2-klein-9B-fp8
# Headless remote reachability. Firmware power-loss recovery is configured
# separately once at the physical machine.
@@ -56,9 +60,6 @@ FAST_MODEL_SHA256=54879ae8738d5938f46cb3b8cbf16bf42b8c85b7d68d7c73f062b612ec183e
MEDIUM_MODEL_FILE=qwen-pure/qwen3.8-27b-IQ4_XS-pure.gguf
MEDIUM_MODEL_URL=https://huggingface.co/jpetrina/Qwen3.8-27B-IQ4_XS-pure-GGUF/resolve/main/qwen3.8-27b-IQ4_XS-pure.gguf
MEDIUM_MODEL_SHA256=ea5a3c45d407f9b9e5d2c0d647f0ea600f486f6b86b92b56d0823ba073dae675
BETA1_MODEL_FILE=qwen3.8-27b-gsq-rco-test/Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp.gguf
BETA1_MODEL_URL=https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF/resolve/main/Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp.gguf
BETA1_MODEL_SHA256=63f29a2189a6b4cc31f81e093d3856ad293a5583114439f41ae1ed7af4093262
LARGE_MODEL_FILE=qwen-pure/qwen3.8-27b-IQ4_XS-pure.gguf
LARGE_MODEL_URL=https://huggingface.co/jpetrina/Qwen3.8-27B-IQ4_XS-pure-GGUF/resolve/main/qwen3.8-27b-IQ4_XS-pure.gguf
LARGE_MODEL_SHA256=ea5a3c45d407f9b9e5d2c0d647f0ea600f486f6b86b92b56d0823ba073dae675
@@ -85,11 +86,6 @@ MEDIUM_CONTEXT=160000
MEDIUM_BATCH_SIZE=2048
MEDIUM_UBATCH_SIZE=128
MEDIUM_TENSOR_SPLIT=85,15
BETA1_CONTEXT=192000
BETA1_BATCH_SIZE=2048
BETA1_UBATCH_SIZE=128
BETA1_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
BETA1_PARALLEL_SLOTS=1
LARGE_CONTEXT=192000
LARGE_BATCH_SIZE=2048
LARGE_UBATCH_SIZE=128
@@ -111,8 +107,6 @@ MEDIUM_PARALLEL_SLOTS=1
LARGE_PARALLEL_SLOTS=1
ULTRA_PARALLEL_SLOTS=1
UNCENSORED_PARALLEL_SLOTS=1
PIPER_TTS_VERSION=1.6.0
PIPER_VOICE=de_DE-thorsten-high
QWEN3_TTS_IMAGE=ghcr.io/malaiwah/qwen3-tts-server:latest@sha256:b363a01d08b1bbecbfc3ca6f585368fae2cfdc591f9ecca6643738369f9a9d98
QWEN3_TTS_CACHE_DIR=/data/models/qwen3-tts-cache
QWEN3_TTS_VOICES_DIR=/data/models/qwen3-tts-voices