.env

@@ -1,8 +1,6 @@
-# https://github.com/ROCm/ROCm/issues/2625
-GPU_MAX_HW_QUEUES=1
-# https://github.com/ROCm/ROCm/issues/2788#issuecomment-1915765846
+# HF_TOKEN=
+PYTORCH_HIP_ALLOC_CONF=garbage_collection_threshold:0.9,max_split_size_mb:512
 HSA_OVERRIDE_GFX_VERSION=11.0.0 # GFX1101/Navi32 (RX 7800XT)
-# PYTORCH_HIP_ALLOC_CONF=garbage_collection_threshold:0.9,max_split_size_mb:512
 
 #=============================================================#
 #                   LibreChat Configuration                   #

README.md

@@ -14,7 +14,7 @@ A quick prototype to self-host [LibreChat](https://github.com/danny-avila/LibreC
 
 ### Prerequisites
 
-* Linux (WSL2 is untested)
+* Linux (WSL2 untested)
 * An AMD 7xxx series GPU (technically optional, Ollama will fallback to using the CPU but it will be very slow. Other GPUS are supported but the deployment must be modified to use them)
 * docker
 * docker-compose
@@ -81,7 +81,7 @@ becomes:
 
 ## Architecture components
 
-* [LibreChat](https://github.com/danny-avila/LibreChat) is a ChatGPT clone with support for multiple AI endpoints. It's deployed alongside a [MongoDB](https://github.com/mongodb/mongo) database and [Meillisearch](https://github.com/meilisearch/meilisearch) for search. It's exposed on http://localhost:3080/.
+* [LibreChat](https://github.com/danny-avila/LibreChat) is a ChatGPT clone with support. It is deployed alongside a [MongoDB](https://github.com/mongodb/mongo) database and [Meillisearch](https://github.com/meilisearch/meilisearch) for search. It is exposed on http://localhost:3080/.
 * [LiteLLM](https://github.com/BerriAI/litellm) is an OpenAI-like API. It is exposed on http://localhost:8000/ without any authentication by default.
 * [Ollama](https://github.com/ollama/ollama) manages and serve the local models.
 

docker-compose.yml

@@ -1,6 +1,5 @@
 version: "3"
 services:
-  # Begin Ollama service
   ollama:
     image: ollama/ollama:0.1.22-rocm
     restart: unless-stopped
@@ -10,7 +9,6 @@ services:
       - .env
     ports:
      - 11434:11434
-    # begin for AMD GPU support
     devices:
       - /dev/kfd
       - /dev/dri
@@ -21,12 +19,10 @@ services:
       - SYS_PTRACE
     security_opt:
       - seccomp=unconfined
-    # end of section for AMD GPU support
     volumes:
       - ./ollama/bootstrap.sh:/bootstrap.sh:ro
       - ollama:/root/.ollama
 
-  # Begin LiteLLM service
   litellm:
     image: ghcr.io/berriai/litellm:main-latest
     command: --config /config.yaml
@@ -35,7 +31,6 @@ services:
     volumes:
       - ./litellm/config.yaml:/config.yaml:ro
 
-  # Begin LibreChat
   librechat:
     image: ghcr.io/danny-avila/librechat
     ports: