post: commit a8a32ef in myai
Some checks failed
Hugo Build & Deploy / build-deploy (push) Has been cancelled
Some checks failed
Hugo Build & Deploy / build-deploy (push) Has been cancelled
This commit is contained in:
50
content/posts/commits/2026-08-11-commit-a8a32ef.md
Normal file
50
content/posts/commits/2026-08-11-commit-a8a32ef.md
Normal file
@@ -0,0 +1,50 @@
|
||||
---
|
||||
title: "[myai] feat(myai): add POST /generate via StarCoder2-3B (GPU)"
|
||||
date: 2026-08-11T17:30:58+02:00
|
||||
draft: false
|
||||
tags: ["commit", "myai", "main"]
|
||||
categories: ["Git Activity"]
|
||||
summary: "Commit a8a32ef par Betty dans myai"
|
||||
author: "Betty"
|
||||
---
|
||||
|
||||
## Commit `a8a32ef`
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| **Repository** | myai |
|
||||
| **Branch** | `main` |
|
||||
| **Author** | Betty |
|
||||
| **Hash** | `a8a32ef01bfe78e041b3ea636d354300dc751063` |
|
||||
|
||||
|
||||
### Description
|
||||
|
||||
- New app/codegen.py: loads bigcode/starcoder2-3b at startup via HuggingFace
|
||||
- POST /generate endpoint: prompt + language → generated code
|
||||
- Dockerfile: switch to pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime base
|
||||
- requirements.txt: add transformers<5.0 + accelerate
|
||||
- stack/myai.yml: GPU placement (nvidia.vgpu), VRAM/CPU limits, hf-cache volume
|
||||
|
||||
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
||||
|
||||
### Files Changed
|
||||
|
||||
```
|
||||
M Dockerfile
|
||||
A app/codegen.py
|
||||
M app/main.py
|
||||
M requirements.txt
|
||||
M stack/myai.yml
|
||||
```
|
||||
|
||||
### Diff Summary
|
||||
|
||||
```
|
||||
Dockerfile | 6 ++++--
|
||||
app/codegen.py | 46 ++++++++++++++++++++++++++++++++++++++++++++++
|
||||
app/main.py | 24 ++++++++++++++++++++++++
|
||||
requirements.txt | 2 ++
|
||||
stack/myai.yml | 20 ++++++++++++++++++--
|
||||
5 files changed, 94 insertions(+), 4 deletions(-)
|
||||
```
|
||||
Reference in New Issue
Block a user