Bump context to 600000 (200000/stream x 3 parallel)

This commit is contained in:
Frank committed 2026-08-07 17:18:10 -07:00
1 parent a5f72627bb
commit 663e47866b
2 files changed
+2 -2

No files matched your search

+1 -1
View File
@@ -7,7 +7,7 @@ set -euo pipefail
SERVER_BIN="/home/dank/llama.cpp/build/bin/llama-server"
PORT="${LLAMA_PORT:-8080}"
N_PARALLEL="${LLAMA_N_PARALLEL:-3}"
CTX_SIZE="${LLAMA_CTX_SIZE:-131072}"
CTX_SIZE="${LLAMA_CTX_SIZE:-600000}"
BATCH_SIZE="${LLAMA_BATCH_SIZE:-4096}"
DRAFT_N_MAX="${LLAMA_DRAFT_N_MAX:-16}"