Set ubatch sweep to requested 32k matrix
This commit is contained in:
@@ -2,8 +2,9 @@
|
||||
# Benchmark ubatch with llama-bench for frank-default-large.
|
||||
#
|
||||
# This is intentionally a ubatch-only benchmark. It uses one llama-bench
|
||||
# process, a fixed 16K prompt workload, and a fixed batch size large enough to
|
||||
# hold that workload. No server process, HTTP requests, or log scraping are used.
|
||||
# process, a fixed 32K prompt workload, and a fixed scheduler size large
|
||||
# enough to hold that workload. No server process, HTTP requests, or log
|
||||
# scraping are used.
|
||||
#
|
||||
# Run on Dankclaw after stopping frank-default-large:
|
||||
# sudo systemctl stop frank-default-large
|
||||
@@ -13,8 +14,8 @@ set -euo pipefail
|
||||
|
||||
: "${LLAMA_BENCH:=/home/dank/GitPackages/ROCmFPX/build-strix-rocmfp4/bin/llama-bench}"
|
||||
: "${MODEL:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP/Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
|
||||
: "${UBATCH_VALUES:=256,512,768,1024,1280,1536,1792,2048,3072,4096,5120,6144}"
|
||||
: "${CONTEXT:=16384}"
|
||||
: "${UBATCH_VALUES:=256,512,768,1024,1280,1536,1792,2048,3072,4096}"
|
||||
: "${CONTEXT:=32768}"
|
||||
: "${GEN_TOKENS:=128}"
|
||||
: "${REPETITIONS:=3}"
|
||||
: "${DEVICE:=ROCm0}"
|
||||
|
||||
Reference in New Issue
Block a user