minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Update kimi k25 launch command in cookbook (#26511)

Browse Source
This commit is contained in:
Qiaolin Yu
2026-05-27 16:04:04 -07:00
committed by GitHub
parent 24bcb37efb
commit 561e54f803
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/src/snippets/autoregressive/kimi-k25-deployment.jsx
+6 -1
View File
@@ -195,7 +195,12 @@ export const KimiK25Deployment = () => {
// Speculative decoding (EAGLE3)
if (speculative === 'enabled') {
cmd += ' \\\n --speculative-algorithm EAGLE3 \\\n --speculative-num-steps 3 \\\n --speculative-eagle-topk 1 \\\n --speculative-num-draft-tokens 4 \\\n --speculative-draft-model-path lightseekorg/kimi-k2.5-eagle3';
cmd += ' \\\n --speculative-algorithm EAGLE3 \\\n --speculative-num-steps 3 \\\n --speculative-eagle-topk 1 \\\n --speculative-num-draft-tokens 4 \\\n --speculative-draft-model-path lightseekorg/kimi-k2.5-eagle3-mla';
}
// Blackwell (B300): tokenspeed MLA attention backend
if (hardware === 'b300') {
cmd += ' \\\n --attention-backend tokenspeed_mla';
}
// AMD: FP8 KV cache for memory efficiency