wrenchpilot
/

presets

Text Generation

Model card Files Files and versions

Merge llama-swap branch into main

#1

by wrenchpilot - opened 15 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

feat: add llama-swap functionality with configuration and preset filesf7e0ee6a

fix: update README to clarify usage of llama-swap and authentication details24d317f7

feat: enhance llama-swap configuration with single-model group and member definitionsd8bdd844

feat: add LLAMA_CACHE environment variable and update cache directory in llama-swap configuration8cb16350

fix: remove unused cache directory option from llama-swap model configurationseb988b1b

fix: remove LLAMA_CACHE environment variable from docker run commanded5f7421

feat: add Qwopus3.6-35B-A3B-Coder-MTP model configuration and presets7e3e2d26

feat: add cache type configurations for Qwopus model43f33a46

feat: add cache type configurations for gemma-4-26B-A4B-it-qat-MTP model3cc44552

feat: add state directory and activity logging for llama-swap61f4d89a

fix: update cache type configurations to q4_0 for gemma-4-26B-A4B-it-qat-MTP model60779cc8

fix: remove cache type configurations from gemma-4-26B-A4B-it-qat-MTP and preset.ini798f8f7b

feat: add llama-swap configuration to .env and update llama-swap.sh for new variablesfd8599e4

fix: correct DOCKER variable assignment in llama-swap.she3b99d3b

fix: remove default variable assignments for CUDA and llama-swap configurations in llama-swap.shdb33f4c0

fix: remove nvidia runtime option from docker run command in llama-swap.she48d5967

fix: remove unnecessary arguments from docker run command in llama-swap.shf17ecb8b

fix: update llama-swap.sh to set LLAMA_SWAP_CONFIG environment variable and remove volume mapping for llama-swap.yaml88c75135

fix: remove Dockerfile.llama-swap build commands from llama-swap.shde1a5e41

fix: enhance server and llama-swap scripts with improved command handling and background executiond0b85331

fix: update .env.example with corrected paths and add service lifecycle section932c841a

fix: correct LLAMA_SWAP_VERSION in .env.example from "cuda-unified" to "unified-cuda"ed126555

fix: update llama-swap gateway to support five active models and enhance configuration settingscefe5cd7

Owner 15 days ago

No description provided.

wrenchpilot changed pull request status to open 15 days ago

wrenchpilot changed pull request status to merged 15 days ago

wrenchpilot deleted the refs/pr/1 ref 15 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment