-
Notifications
You must be signed in to change notification settings - Fork 532
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[Examples] Add qwen-110B and fix GUI (#3489)
* Add qwen-110B * Add qwen-110B * fix GUI * minor * minor * use vllm gradio * Add gif and to ai gallery * add new label * add llama3 and qwen to readmes
- Loading branch information
1 parent
889adce
commit 1e5246d
Showing
8 changed files
with
71 additions
and
28 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
../../../../llm/qwen/README.md |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,43 @@ | ||
envs: | ||
MODEL_NAME: Qwen/Qwen1.5-110B-Chat | ||
|
||
service: | ||
# Specifying the path to the endpoint to check the readiness of the replicas. | ||
readiness_probe: | ||
path: /v1/chat/completions | ||
post_data: | ||
model: $MODEL_NAME | ||
messages: | ||
- role: user | ||
content: Hello! What is your name? | ||
max_tokens: 1 | ||
initial_delay_seconds: 1200 | ||
# How many replicas to manage. | ||
replicas: 2 | ||
|
||
|
||
resources: | ||
accelerators: {A100:8, A100-80GB:4, A100-80GB:8} | ||
disk_size: 1024 | ||
disk_tier: best | ||
memory: 32+ | ||
ports: 8000 | ||
|
||
setup: | | ||
conda activate qwen | ||
if [ $? -ne 0 ]; then | ||
conda create -n qwen python=3.10 -y | ||
conda activate qwen | ||
fi | ||
pip install -U vllm==0.4.1 | ||
pip install -U transformers==4.38.0 | ||
run: | | ||
conda activate qwen | ||
export PATH=$PATH:/sbin | ||
python -u -m vllm.entrypoints.openai.api_server \ | ||
--host 0.0.0.0 \ | ||
--model $MODEL_NAME \ | ||
--tensor-parallel-size $SKYPILOT_NUM_GPUS_PER_NODE \ | ||
--max-num-seqs 16 | tee ~/openai_api_server.log | ||