"hidden_size": 4096, "kv_channels": 128, "layernorm_epsilon": 1e-05, "model_type": "chatglm", "multi_query_attention": true, "multi_query_group_num": 2, "num_attention_heads": 32, "num_layers": 28, "original_rope": true, "pad_token_id": 0, "padded_vocab_size": 65024,...
(f"vLLM is using nccl=={ncclGetVersion()}") ERROR 04-24 02:01:17 worker_base.py:157] NameError: name 'ncclGetVersion' is not defined Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals...
tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, enable_lora=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', max_cpu_loras=None, device='auto', image_input_type=None, image_token_id=None, image_input_shape=None...
55 except core._NotOkStatusException as e: 56 if name is not None: UnimplementedError: Graph execution error: Detected at node functional_5_1/Cast defined at (most recent call last): File "/home/jinqi_shen/.airconda-environments/production--payments--tensorflow--ray_tf215--v0.0.1/lib/pyt...