remove DEFAULT_ARGS that are none, fix MAX_CONTEXT_LEN_TO_CAPTURE

src/engine_args.py

@@ -12,7 +12,6 @@ ENV_ALIASES = {
     "MODEL_NAME": "model",
     "MODEL_REVISION": "revision",
     "TOKENIZER_NAME": "tokenizer",
-    "MAX_CONTEXT_LEN_TO_CAPTURE": "max_seq_len_to_capture",
 }
 
 # Literal defaults from original worker (used when env/local do not set a value)
@@ -22,41 +21,26 @@ DEFAULT_ARGS = {
     "gpu_memory_utilization": 0.95,
     "pipeline_parallel_size": 1,
     "tensor_parallel_size": 1,
-    "served_model_name": None,
-    "tokenizer": None,
     "skip_tokenizer_init": False,
     "tokenizer_mode": "auto",
     "trust_remote_code": False,
-    "download_dir": None,
     "load_format": "auto",
     "dtype": "auto",
     "kv_cache_dtype": "auto",
-    "quantization_param_path": None,
     "seed": 0,
-    "max_model_len": None,
     "worker_use_ray": False,
-    "distributed_executor_backend": None,
-    "max_parallel_loading_workers": None,
     "block_size": 16,
     "enable_prefix_caching": False,
     "disable_sliding_window": False,
     "swap_space": 4,
     "cpu_offload_gb": 0,
-    "max_num_batched_tokens": None,
     "max_num_seqs": 256,
     "max_logprobs": 20,
-    "revision": None,
-    "code_revision": None,
-    "rope_scaling": None,
-    "rope_theta": None,
-    "tokenizer_revision": None,
-    "quantization": None,
     "enforce_eager": False,
     "max_seq_len_to_capture": 8192,
     "disable_custom_all_reduce": False,
     "tokenizer_pool_size": 0,
     "tokenizer_pool_type": "ray",
-    "tokenizer_pool_extra_config": None,
     "enable_lora": False,
     "max_loras": 1,
     "max_lora_rank": 16,
@@ -65,32 +49,13 @@ DEFAULT_ARGS = {
     "max_prompt_adapter_token": 0,
     "fully_sharded_loras": False,
     "lora_extra_vocab_size": 256,
-    "long_lora_scaling_factors": None,
     "lora_dtype": "auto",
-    "max_cpu_loras": None,
     "device": "auto",
     "ray_workers_use_nsight": False,
-    "num_gpu_blocks_override": None,
     "num_lookahead_slots": 0,
-    "model_loader_extra_config": None,
-    "ignore_patterns": None,
-    "preemption_mode": None,
     "scheduler_delay_factor": 0.0,
-    "enable_chunked_prefill": None,
     "guided_decoding_backend": "outlines",
-    "speculative_model": None,
-    "speculative_draft_tensor_parallel_size": None,
-    "num_speculative_tokens": None,
-    "speculative_max_model_len": None,
-    "speculative_disable_by_batch_size": None,
-    "ngram_prompt_lookup_max": None,
-    "ngram_prompt_lookup_min": None,
     "spec_decoding_acceptance_method": "rejection_sampler",
-    "typical_acceptance_sampler_posterior_threshold": None,
-    "typical_acceptance_sampler_posterior_alpha": None,
-    "qlora_adapter_name_or_path": None,
-    "disable_logprobs_during_spec_decoding": None,
-    "otlp_traces_endpoint": None,
     "stream_interval": 1,
 
 }