2026-04-18 22:34:20 TP0] model.eh_proj.weight_scale not found in params_dict.
[2026-04-18 22:34:20 TP7] Scheduler hit an exception: Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 3771, in run_scheduler_process
    scheduler = Scheduler(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 425, in __init__
    self.init_model_worker()
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 683, in init_model_worker
    self.maybe_init_draft_worker()
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 667, in maybe_init_draft_worker
    self.draft_worker = DraftWorkerClass(**draft_worker_kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/speculative/eagle_worker_v2.py", line 658, in __init__
    self._draft_worker = EagleDraftWorker(
  File "/sgl-workspace/sglang/python/sglang/srt/speculative/eagle_worker_v2.py", line 138, in __init__
    self.draft_worker = TpModelWorker(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 260, in __init__
    self._init_model_runner()
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 343, in _init_model_runner
    self._model_runner = ModelRunner(
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 480, in __init__
    self.initialize(pre_model_load_memory)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 570, in initialize
    self.load_model()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 1264, in load_model
    self.model = self.loader.load_model(
  File "/sgl-workspace/sglang/python/sglang/srt/model_loader/loader.py", line 699, in load_model
    self.load_weights_and_postprocess(
  File "/sgl-workspace/sglang/python/sglang/srt/model_loader/loader.py", line 708, in load_weights_and_postprocess
    model.load_weights(weights)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_nextn.py", line 284, in load_weights
    super().load_weights(weights, is_nextn=True)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 2323, in load_weights
    self.do_load_weights(weights, is_nextn)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_common/deepseek_weight_loader.py", line 361, in do_load_weights
    future.result()

python3 -m sglang.launch_server \
    --model-path $MODEL \
    --host=0.0.0.0 \
    --port $PORT \
    --trust-remote-code \
    --tp $TP \
    --chunked-prefill-size 131072 \
    --disable-radix-cache \
    --mem-fraction-static 0.85 \
    --model-loader-extra-config '{"enable_multithread_load": true}' \
    --watchdog-timeout 1200 \
    --reasoning-parser glm45 \
    --tool-call-parser glm47 \
    --speculative-algorithm EAGLE \
    --speculative-num-steps 3 \
    --speculative-eagle-topk 1 \
    --speculative-num-draft-tokens 4 \
    $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &