github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-04-29 03:00:14 -04:00
Code Issues Packages Projects Releases Wiki Activity

llm: buffer SSE chunks to fix parse errors from split reads (#15641)

Browse Source
This commit is contained in:
b1tg
2026-04-08 10:26:23 +08:00
committed by GitHub
parent a508b8fd2a
commit bf3763526a
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tinygrad/apps/llm.py
View File

@@ -313,10 +313,14 @@ CHAT_HTML = b'''<!DOCTYPE html><html><head><title>tinygrad chat</title><style>
const d = document.createElement('div'); d.className = 'msg'; chat.appendChild(d);
const r = await fetch('/v1/chat/completions', {method: 'POST', headers: {'Content-Type': 'application/json'},
body: JSON.stringify({model: 'llama', messages: msgs, stream: true, temperature: 0.7})});
let buf = '';
for (const rd = r.body.getReader(), dec = new TextDecoder();;) {
const {done, value} = await rd.read();
if (done) break;
for (const ln of dec.decode(value).split('\\n'))
buf += dec.decode(value, {stream: true});
const lines = buf.split('\\n');
buf = lines.pop();
for (const ln of lines)
if (ln.startsWith('data: ') && !ln.includes('[DONE]'))
try { d.textContent += JSON.parse(ln.slice(6)).choices[0]?.delta?.content || '' } catch {}
chat.scrollTop = chat.scrollHeight;