marc
/
Cortex
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

compose-vLLM.yml aktualisiert

This commit is contained in:
Marc Blatter 2026-07-15 19:34:24 +00:00
parent 1e245cb58b
commit 9cb6cbc909
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
compose-vLLM.yml
View File

@ -38,8 +38,12 @@ services:
- "0.90" - "0.90"
- "--max-model-len" - "--max-model-len"
- "65536" - "65536"
- "--rope-scaling"
- '{"rope_type":"yarn","factor":2.0,"original_max_position_embeddings":40960}'
- "--max-num-seqs" - "--max-num-seqs"
- "32" - "16"
- "--kv-cache-dtype"
- "fp8"
- "--enable-prefix-caching" - "--enable-prefix-caching"
- "--enable-auto-tool-choice" - "--enable-auto-tool-choice"
- "--tool-call-parser" - "--tool-call-parser"