large: disable target greedy argmax fast path for chat (Kairic)

The pinned runner sets LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1, but the
exact-Q8 argmax fast path fails closed on any non-greedy request. The
model card's own chat instructions override sampling per request with
Qwen live values (temp 0.7, top-p 0.8, top-k 20, min-p 0,
presence_penalty 1.5), which the fast path rejects (400). Production
chat forces the fast path to 0; the Kairic IU4 lane (--kairic-edge) and
the MTP draft fast path are unaffected.
This commit is contained in:
Frank
2026-08-22 00:28:01 -07:00
parent 4c438390dd
commit 7aee1df7c3
+10 -1
View File
@@ -88,7 +88,16 @@ export LD_LIBRARY_PATH="$(dirname "$LLAMA_BIN"):${ROCM_LIB}/lib:${ROCM_CORE}/lib
export HIP_VISIBLE_DEVICES=0
export HSA_OVERRIDE_GFX_VERSION=11.5.1
export GGML_CUDA_GRAPH_OPT=0
export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1
# The pinned runner sets the target exact-Q8 greedy argmax fast path
# (LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1). That fast path fails closed on
# any non-greedy request (temperature != 0, top_k > 1, top_p < 1, penalties,
# grammar, logit bias, or reasoning budget). The model card's own chat
# instructions override sampling per request with Qwen live values (temp
# 0.7, top-p 0.8, top-k 20, min-p 0, presence_penalty 1.5), which the fast
# path rejects. Production chat therefore forces it to 0. This does NOT
# affect the Kairic Edge IU4 lane (prompt/verification route via
# --kairic-edge) nor the MTP draft fast path below.
export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0
export LLAMA_MTP_CPU_ARGMAX_FASTPATH=1
export PROMPTFORGE_TARGET_ONLY=0
export PROMPTFORGE_MODE=iu4_ffn