dank/serverAppConfigs
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Frank
2026-08-07 17:18:10 -07:00
parent a5f72627bb
commit 663e47866b
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/llama-server.service
+1 -1
View File
@@ -6,7 +6,7 @@ After=network.target
Type=simple
User=dank
Group=dank
ExecStart=/home/dank/llama.cpp/build/bin/llama-server --hf-repo unsloth/Qwen3.6-27B-MTP-GGUF:Q8_0 --spec-draft-hf Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp:Q8_0 --spec-type draft-dflash --spec-draft-n-max 16 --device ROCm0 --spec-draft-device ROCm0 --gpu-layers all --fit on --fit-target 512 --parallel 3 --ctx-size 131072 --batch-size 4096 --port 8080 --host 0.0.0.0 --threads 16 --alias frank-default-large --load-mode none
ExecStart=/home/dank/llama.cpp/build/bin/llama-server --hf-repo unsloth/Qwen3.6-27B-MTP-GGUF:Q8_0 --spec-draft-hf Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp:Q8_0 --spec-type draft-dflash --spec-draft-n-max 16 --device ROCm0 --spec-draft-device ROCm0 --gpu-layers all --fit on --fit-target 512 --parallel 3 --ctx-size 600000 --batch-size 4096 --port 8080 --host 0.0.0.0 --threads 16 --alias frank-default-large --load-mode none
Restart=on-failure
RestartSec=10
scripts/serve-llamacpp-dflash.sh
+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}"