Delete int4_awq

int4_awq/config.json

@@ -1,174 +0,0 @@
-{
-    "version": "0.13.0",
-    "pretrained_config": {
-        "mlp_bias": false,
-        "attn_bias": false,
-        "rotary_base": 500000.0,
-        "rotary_scaling": {
-            "factor": 8.0,
-            "low_freq_factor": 1.0,
-            "high_freq_factor": 4.0,
-            "original_max_position_embeddings": 8192,
-            "rope_type": "llama3"
-        },
-        "residual_mlp": false,
-        "disable_weight_only_quant_plugin": false,
-        "moe": {
-            "num_experts": 0,
-            "top_k": 0,
-            "normalization_mode": 1,
-            "sparse_mixer_epsilon": 0.01,
-            "tp_mode": 0
-        },
-        "remove_duplicated_kv_heads": false,
-        "architecture": "LlamaForCausalLM",
-        "dtype": "float16",
-        "vocab_size": 128256,
-        "hidden_size": 4096,
-        "num_hidden_layers": 32,
-        "num_attention_heads": 32,
-        "hidden_act": "silu",
-        "logits_dtype": "float16",
-        "norm_epsilon": 1e-05,
-        "position_embedding_type": "rope_gpt_neox",
-        "max_position_embeddings": 131072,
-        "num_key_value_heads": 8,
-        "intermediate_size": 14336,
-        "mapping": {
-            "world_size": 1,
-            "gpus_per_node": 8,
-            "cp_size": 1,
-            "tp_size": 1,
-            "pp_size": 1,
-            "moe_tp_size": 1,
-            "moe_ep_size": 1
-        },
-        "quantization": {
-            "quant_algo": "W4A16_AWQ",
-            "kv_cache_quant_algo": null,
-            "group_size": 128,
-            "smoothquant_val": 0.5,
-            "clamp_val": null,
-            "has_zero_point": false,
-            "pre_quant_scale": true,
-            "exclude_modules": [
-                "lm_head"
-            ]
-        },
-        "use_parallel_embedding": true,
-        "embedding_sharding_dim": 0,
-        "share_embedding_table": false,
-        "head_size": 128,
-        "qk_layernorm": false,
-        "producer": {
-            "name": "modelopt",
-            "version": "0.15.1"
-        },
-        "bias": false,
-        "rotary_pct": 1.0,
-        "rank": 0,
-        "decoder": "llama",
-        "rmsnorm": true,
-        "lm_head_bias": false
-    },
-    "build_config": {
-        "max_input_len": 1048576,
-        "max_seq_len": 1048576,
-        "opt_batch_size": null,
-        "max_batch_size": 64,
-        "max_beam_width": 1,
-        "max_num_tokens": 65536,
-        "opt_num_tokens": 64,
-        "max_prompt_embedding_table_size": 0,
-        "kv_cache_type": "PAGED",
-        "gather_context_logits": false,
-        "gather_generation_logits": false,
-        "strongly_typed": true,
-        "builder_opt": null,
-        "force_num_profiles": null,
-        "profiling_verbosity": "layer_names_only",
-        "enable_debug_output": false,
-        "max_draft_len": 0,
-        "speculative_decoding_mode": 1,
-        "use_refit": false,
-        "input_timing_cache": null,
-        "output_timing_cache": "model.cache",
-        "lora_config": {
-            "lora_dir": [],
-            "lora_ckpt_source": "hf",
-            "max_lora_rank": 64,
-            "lora_target_modules": [],
-            "trtllm_modules_to_hf_modules": {}
-        },
-        "auto_parallel_config": {
-            "world_size": 1,
-            "gpus_per_node": 8,
-            "cluster_key": "A100-SXM-40GB",
-            "cluster_info": null,
-            "sharding_cost_model": "alpha_beta",
-            "comm_cost_model": "alpha_beta",
-            "enable_pipeline_parallelism": false,
-            "enable_shard_unbalanced_shape": false,
-            "enable_shard_dynamic_shape": false,
-            "enable_reduce_scatter": true,
-            "builder_flags": null,
-            "debug_mode": false,
-            "infer_shape": true,
-            "validation_mode": false,
-            "same_buffer_io": {
-                "past_key_value_(\\d+)": "present_key_value_\\1"
-            },
-            "same_spec_io": {},
-            "sharded_io_allowlist": [
-                "past_key_value_\\d+",
-                "present_key_value_\\d*"
-            ],
-            "fill_weights": false,
-            "parallel_config_cache": null,
-            "profile_cache": null,
-            "dump_path": null,
-            "debug_outputs": []
-        },
-        "weight_sparsity": false,
-        "weight_streaming": false,
-        "plugin_config": {
-            "dtype": "float16",
-            "bert_attention_plugin": "auto",
-            "gpt_attention_plugin": "auto",
-            "gemm_plugin": "auto",
-            "gemm_swiglu_plugin": null,
-            "fp8_rowwise_gemm_plugin": null,
-            "smooth_quant_gemm_plugin": null,
-            "identity_plugin": null,
-            "layernorm_quantization_plugin": null,
-            "rmsnorm_quantization_plugin": null,
-            "nccl_plugin": null,
-            "lookup_plugin": null,
-            "lora_plugin": null,
-            "weight_only_groupwise_quant_matmul_plugin": "float16",
-            "weight_only_quant_matmul_plugin": null,
-            "quantize_per_token_plugin": false,
-            "quantize_tensor_plugin": false,
-            "moe_plugin": "auto",
-            "mamba_conv1d_plugin": "auto",
-            "low_latency_gemm_plugin": null,
-            "context_fmha": true,
-            "bert_context_fmha_fp32_acc": false,
-            "paged_kv_cache": true,
-            "remove_input_padding": true,
-            "reduce_fusion": false,
-            "enable_xqa": true,
-            "tokens_per_block": 64,
-            "use_paged_context_fmha": false,
-            "use_fp8_context_fmha": false,
-            "multiple_profiles": false,
-            "paged_state": false,
-            "streamingllm": false,
-            "manage_weights": false,
-            "use_fused_mlp": true
-        },
-        "use_strip_plan": false,
-        "max_encoder_input_len": 1024,
-        "use_fused_mlp": false
-    }
-}

int4_awq/rank0.engine

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:28d52f9163135bb202bc5c1e76060ca0e87f88f85f70969c56ee34010fa4baad
-size 5778055484