feat(910c/glm52): 并行配置改为只测 TP=8 和 TP=16,并按TP区分服务参数

config.env: PARALLEL_CONFIGS 默认值从 "2 4"/"4 2"/"8 1" 改为 "8 1"/"16 1"
run_adaptive_concurrency_add16.sh: engine_build_server_args 按 TP 覆盖参数
- TP=8:  gpu_mem_util=0.95, max_model_len=16384,  max_num_seqs=64  (64GB/die KV cache 紧张)
- TP=16: gpu_mem_util=0.92, max_model_len=131072, max_num_seqs=256 (16 die 全用)
可通过 TP8_*/TP16_* 环境变量进一步覆盖

experiments/910c/glm52_910c_vllm_tp_dp_matrix/config.env

@@ -47,9 +47,9 @@ export CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0,1,2,3,4,5,6,7}"
 RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"
 
 # Parallel configurations to test. Format: "TP DP"
-# Each Ascend910 card has 2 dies; TP addresses dies, so TP=8 uses 8 dies across
-# 4 cards and leaves room for DP. TP=2/DP=4 and TP=4/DP=2 and TP=8/DP=1 all fit
-# within 8 cards (16 dies). Override via PARALLEL_CONFIGS_STR="8,1".
+# Each Ascend910 card has 2 dies; TP addresses dies. TP=8 uses 8 dies (4 cards),
+# TP=16 uses all 16 dies (8 cards). Only these two configs are tested.
+# Override via PARALLEL_CONFIGS_STR="8,1 16,1" (space-separated).
 if [[ -n "${PARALLEL_CONFIGS_STR:-}" ]]; then
   declare -a PARALLEL_CONFIGS=()
   for pair in $PARALLEL_CONFIGS_STR; do
@@ -57,9 +57,8 @@ if [[ -n "${PARALLEL_CONFIGS_STR:-}" ]]; then
   done
 else
   declare -a PARALLEL_CONFIGS=(
-    "2 4"
-    "4 2"
     "8 1"
+    "16 1"
   )
 fi
 

experiments/910c/glm52_910c_vllm_tp_dp_matrix/run_adaptive_concurrency_add16.sh

@@ -74,6 +74,24 @@ engine_stop_server() {
 engine_build_server_args() {
   local tp="$1"
   local dp="$2"
+  # Per-TP overrides: TP=8 has tight KV cache on 64GB/die (cap context/seqs),
+  # TP=16 uses all 16 dies and can serve the full 128K context.
+  local mem_util="$GPU_MEMORY_UTILIZATION"
+  local max_len="$MAX_MODEL_LEN"
+  local max_seqs="$MAX_NUM_SEQS"
+  case "$tp" in
+    8)
+      mem_util="${TP8_GPU_MEMORY_UTILIZATION:-0.95}"
+      max_len="${TP8_MAX_MODEL_LEN:-16384}"
+      max_seqs="${TP8_MAX_NUM_SEQS:-64}"
+      ;;
+    16)
+      mem_util="${TP16_GPU_MEMORY_UTILIZATION:-0.92}"
+      max_len="${TP16_MAX_MODEL_LEN:-131072}"
+      max_seqs="${TP16_MAX_NUM_SEQS:-256}"
+      ;;
+  esac
+  log "server args tp=${tp} dp=${dp} gpu_mem_util=${mem_util} max_model_len=${max_len} max_num_seqs=${max_seqs}" >&2
   local -a args=(
     vllm serve "$MODEL_PATH"
     --served-model-name "$SERVED_MODEL_NAME"
@@ -81,9 +99,9 @@ engine_build_server_args() {
     --kv-cache-dtype "$KV_CACHE_DTYPE"
     --block-size "$BLOCK_SIZE"
     --tensor-parallel-size "$tp"
-    --gpu-memory-utilization "$GPU_MEMORY_UTILIZATION"
-    --max-model-len "$MAX_MODEL_LEN"
-    --max-num-seqs "$MAX_NUM_SEQS"
+    --gpu-memory-utilization "$mem_util"
+    --max-model-len "$max_len"
+    --max-num-seqs "$max_seqs"
     --host 0.0.0.0
     --port "$ENGINE_PORT"
   )