bench: add prod2048 config (runner batch sizes on chat profile); docs: ubatch 4096 results
This commit is contained in:
@@ -9,6 +9,7 @@
|
||||
# nofast runner + fast path OFF
|
||||
# prod production profile (b4096/ub4096, --no-mmap, reasoning on/deepseek,
|
||||
# fast path OFF, preserve_thinking)
|
||||
# prod2048 prod with the pinned runner's batch sizes (b2048/ub512)
|
||||
# prodnommap (obsolete: identical to prod since ubatch 4096 + --no-mmap
|
||||
# moved into the production profile)
|
||||
#
|
||||
@@ -63,6 +64,7 @@ case "$CFG" in
|
||||
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=4096; REA=on; RFMT=deepseek; EXTRA="--chat-template-kwargs {\"preserve_thinking\":\"true\"}"; MMAP="--no-mmap" ;;
|
||||
prod2048) export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0; B=2048; UB=512; 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
|
||||
|
||||
|
||||
Reference in New Issue
Block a user