large: ubatch 4096 (match v3), add --no-mmap; sync bench harness prod config

This commit is contained in:
Frank committed 2026-08-22 03:02:16 -07:00
1 parent 0f2bb636d7
commit bd9d75af3f
3 files changed
+19 -12

No files matched your search

+4 -3
View File
@@ -7,9 +7,10 @@
# greedy argmax fast path ON)
# nommap runner + --no-mmap
# nofast runner + fast path OFF
# prod production profile (b4096/ub2048, reasoning on/deepseek,
# prod production profile (b4096/ub4096, --no-mmap, reasoning on/deepseek,
# fast path OFF, preserve_thinking)
# prodnommap prod + --no-mmap
# prodnommap (obsolete: identical to prod since ubatch 4096 + --no-mmap
# moved into the production profile)
#
# Usage: ./scripts/bench-kairic-ab.sh <cfg> [ctx] [prompt_chars]
# Example: ./scripts/bench-kairic-ab.sh prod 16384 53000
@@ -61,7 +62,7 @@ case "$CFG" in
runner) export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1; B=2048; UB=512; REA=off; RFMT=none; EXTRA="" ;;
nommap) export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1; B=2048; UB=512; REA=off; RFMT=none; EXTRA=""; MMAP="--no-mmap" ;;
nofast) export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0; B=2048; UB=512; REA=off; RFMT=none; EXTRA="" ;;
prod) export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0; B=4096; UB=2048; REA=on; RFMT=deepseek; EXTRA="--chat-template-kwargs {\"preserve_thinking\":\"true\"}" ;;
prod) export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0; B=4096; UB=4096; REA=on; RFMT=deepseek; EXTRA="--chat-template-kwargs {\"preserve_thinking\":\"true\"}"; MMAP="--no-mmap" ;;
prodnommap) export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0; B=4096; UB=2048; REA=on; RFMT=deepseek; EXTRA="--chat-template-kwargs {\"preserve_thinking\":\"true\"}"; MMAP="--no-mmap" ;;
esac