fix(p800): managed-mode server startup and smoke-test defaults

- Remove USE_FAST_BFP16_MOE=1 which caused torch parameter assignment
  crash in fresh containers for w8a8_int8 mode.
- Mount model path at its host absolute path inside the container so the
  bench client tokenizer can load it regardless of server --model-path.
- Default WARMUP to 0 and NUM_PROMPTS to 10 for a fast smoke test.
- Default to a single scenario; document how to run a full grid.
- Update experiment README with PLATFORM env var and override examples.

experiments/dsv4_p800_sglang/README.md

@@ -5,15 +5,27 @@ Kunlun P800 XPU + SGLang + `DeepSeek-V4-Flash-INT8` benchmark experiment.
 ## Quick Start
 
 ```bash
-# Run all configured scenarios (starts server, runs benchmark, stops server)
-bash experiments/dsv4_p800_sglang/run_bench.sh
+# Run the default smoke-test scenario (starts server, runs benchmark, stops server)
+PLATFORM=kunlun_p800 bash experiments/dsv4_p800_sglang/run_bench.sh
 
 # Reuse an already-running server
-SKIP_MANAGE_SERVER=1 bash experiments/dsv4_p800_sglang/run_bench.sh
+SKIP_MANAGE_SERVER=1 PLATFORM=kunlun_p800 bash experiments/dsv4_p800_sglang/run_bench.sh
 ```
 
 Results land in `experiments/dsv4_p800_sglang/results/<RUN_ID>/`.
 
+## Configuration
+
+Edit `config.env` or override via environment variables:
+
+```bash
+# Run a full throughput grid instead of the default single smoke-test scenario
+SCENARIOS=("32 512 256" "128 512 256" "256 512 256" "512 512 256") \
+NUM_PROMPTS=512 \
+PLATFORM=kunlun_p800 \
+bash experiments/dsv4_p800_sglang/run_bench.sh
+```
+
 ## Files
 
 | File | Purpose |

experiments/dsv4_p800_sglang/config.env

@@ -14,22 +14,23 @@ DATASET="${DATASET:-random}"
 # platforms/patches/kunlun_p800/dummy_sharegpt.json; for managed mode it is
 # mounted to /workspace/dummy_sharegpt.json.
 DATASET_PATH="${DATASET_PATH:-/workspace/dummy_sharegpt.json}"
-WARMUP="${WARMUP:-100}"
-NUM_PROMPTS="${NUM_PROMPTS:-512}"
+WARMUP="${WARMUP:-0}"
+# Default to a small number of prompts for a quick smoke test. Increase to 512
+# or more for a real throughput measurement.
+NUM_PROMPTS="${NUM_PROMPTS:-10}"
 
 # Server launch mode for P800 SGLang.
 #   - "fp8"      : non-INT8 DeepSeek-V4-Flash checkpoint
 #   - "w8a8_int8": DeepSeek-V4-Flash-INT8 checkpoint
 SERVER_MODE="${SERVER_MODE:-w8a8_int8}"
 
-# Scenario list: "concurrency input_len output_len" (one per line)
-# Override example: SCENARIOS=("32 512 256")
+# Scenario list: "concurrency input_len output_len" (one per line).
+# Default to a single smoke-test scenario for fast validation. Override to run
+# a full grid, e.g.:
+#   SCENARIOS=("32 512 256" "128 512 256" "256 512 256" "512 512 256")
 if [[ -z "${SCENARIOS:-}" ]]; then
   SCENARIOS=(
     "32 512 256"
-    "128 512 256"
-    "256 512 256"
-    "512 512 256"
   )
 fi
 

scripts/common/server_docker.sh

@@ -101,7 +101,6 @@ docker_server_start() {
     -e XINFER_QUANT_SDNN=1
     -e XSGL_USE_MOE_SIGMOID_GROUP_TOPK_NORM=1
     -e XSGL_EARLY_FIRST_TOKEN=1
-    -e USE_FAST_BFP16_MOE=1
     -e XSGL_ENABLE_TGEMM_FP16=1
     -e SGLANG_ENABLE_SPEC_V2=True
     -e SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
@@ -189,6 +188,7 @@ EOF
     --ipc host \
     ${device_args} \
     -v "${model_path}:/models:ro" \
+    -v "${model_path}:${model_path}:ro" \
     "${patch_mounts[@]}" \
     "${env_args[@]}" \
     "${image}" \