more bug fixes.

This commit is contained in:
2026-02-12 05:36:15 -05:00
parent 72681217ef
commit b2d2252342
5 changed files with 8 additions and 11 deletions

View File

@@ -20,7 +20,7 @@ spec:
spec:
containers:
- name: gradio
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120526
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120535
imagePullPolicy: Always
command: ["python", "embeddings.py"]
ports:

11
llm.py
View File

@@ -218,18 +218,15 @@ Chat with **Llama 3.1 70B** (AWQ INT4) served via vLLM on AMD Strix Halo (ROCm).
with gr.TabItem("💬 Chat"):
chatbot = gr.ChatInterface(
fn=chat_stream,
type="messages",
additional_inputs=[system_prompt, temperature, max_tokens, top_p],
examples=[
"Hello! What can you tell me about yourself?",
"Explain how a GPU executes a matrix multiplication.",
"Write a Python function to compute the Fibonacci sequence.",
"What are the pros and cons of running LLMs on AMD GPUs?",
["Hello! What can you tell me about yourself?"],
["Explain how a GPU executes a matrix multiplication."],
["Write a Python function to compute the Fibonacci sequence."],
["What are the pros and cons of running LLMs on AMD GPUs?"],
],
chatbot=gr.Chatbot(
height=520,
type="messages",
show_copy_button=True,
placeholder="Type a message to start chatting...",
),
)

View File

@@ -20,7 +20,7 @@ spec:
spec:
containers:
- name: gradio
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120526
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120535
imagePullPolicy: Always
command: ["python", "llm.py"]
ports:

View File

@@ -20,7 +20,7 @@ spec:
spec:
containers:
- name: gradio
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120526
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120535
imagePullPolicy: Always
command: ["python", "stt.py"]
ports:

View File

@@ -20,7 +20,7 @@ spec:
spec:
containers:
- name: gradio
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120526
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120535
imagePullPolicy: Always
command: ["python", "tts.py"]
ports: