haylan/LLM-Server
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

chore(env): lower DFlash2 --spec-draft-n-max to 3 for long-context acceptance

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
haylanandClaude Bot committed 2026-11-06 18:49:05 +01:00
1 parent 9fbdf3e664
commit 6ce527741b
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+1 -1
View File
@@ -9,7 +9,7 @@ LLAMA_CACHE_RAM=0
LLAMA_KV_CACHE_TYPE=q8_0 LLAMA_KV_CACHE_TYPE=q8_0
# Blank = speculative decoding off; see docs/architecture.md#llama-server # Blank = speculative decoding off; see docs/architecture.md#llama-server
LLAMA_SPEC_ARGS=--spec-type draft-dflash -md /models/Qwen3.8-27B-DFlash2-Q8_0.gguf --spec-draft-n-max 7 LLAMA_SPEC_ARGS=--spec-type draft-dflash -md /models/Qwen3.8-27B-DFlash2-Q8_0.gguf --spec-draft-n-max 3
# --- SearXNG web search --- see docs/gateway.md#web-search # --- SearXNG web search --- see docs/gateway.md#web-search
# Auto-filled by update.sh — leave blank. # Auto-filled by update.sh — leave blank.