[Docs] Add Doc for Online quantification (#6399)

* add doc for dynamic quant

* check

docs/parameters.md

@@ -24,7 +24,7 @@ When using FastDeploy to deploy models (including offline inference and service
 | ```use_warmup``` | `int` | Whether to perform warmup at startup, will automatically generate maximum length data for warmup, default: 0 (disabled) |
 | ```limit_mm_per_prompt``` | `dict[str]` | Limit the amount of multimodal data per prompt, e.g.: {"image": 10, "video": 3}, default: 1 for all |
 | ```enable_mm``` | `bool` | __[DEPRECATED]__ Whether to support multimodal data (for multimodal models only), model architecture automatically detects multimodal models, no manual setting needed |
-| ```quantization``` | `str` | Model quantization strategy, when loading BF16 CKPT, specifying wint4 or wint8 supports lossless online 4bit/8bit quantization |
+| ```quantization``` | `str` | Model Quantization Strategy: When loading a BF16 checkpoint (CKPT), specifying `wint4`, `wint8`, `block_wise_fp8` or `wfp8afp8` enables lossless online 4-bit/8-bit quantization of weights, KVCache is not quantized by default; if this parameter is parsed as a dictionary (dict), `mix_quant` (mixed quantization) can be specified, where `dense_quant_type`, `moe_quant_type` and `kv_cache_quant_type` specify the quantization types for DenseGEMM, MoE and KVCache respectively, no quantization is applied to the corresponding modules if the relevant parameters are not specified (e.g., `'{"quantization":"mix_quant","dense_quant_type":"wint8","moe_quant_type":"wint4","kv_cache_quant_type":"block_wise_fp8"}'`); Note: Online quantization of KVCache to `block_wise_fp8` is only supported by the AppendAttn backend. |
 | ```gpu_memory_utilization``` | `float` | GPU memory utilization, default: 0.9 |
 | ```num_gpu_blocks_override``` | `int` | Preallocated KVCache blocks, this parameter can be automatically calculated by FastDeploy based on memory situation, no need for user configuration, default: None |
 | ```max_num_batched_tokens``` | `int` | Maximum batch token count in Prefill phase, default: None (same as max_model_len) |

docs/zh/parameters.md

@@ -22,7 +22,7 @@
 | ```use_warmup```                   | `int`      | 是否在启动时进行warmup，会自动生成极限长度数据进行warmup，默认0（不启用） |
 | ```limit_mm_per_prompt```          | `dict[str]` | 限制每个prompt中多模态数据的数量，如：{"image": 10, "video": 3}，默认都为1 |
 | ```enable_mm```                    | `bool`      | __[已废弃]__ 是否支持多模态数据（仅针对多模模型），模型架构会自动检测是否为多模态模型，无需手动设置 |
-| ```quantization```                 | `str`       | 模型量化策略，当在加载BF16 CKPT时，指定wint4或wint8时，支持无损在线4bit/8bit量化 |
+| ```quantization```                 | `str`       | 模型量化策略，当在加载BF16 CKPT时，指定wint4、wint8、block_wise_fp8、wfp8afp8时，支持权重无损在线4bit/8bit量化，默认不量化KVCache。如果该参数会被解析为dict，可指定`mix_quant`混合量化，其中`dense_quant_type`、`moe_quant_type`和`kv_cache_quant_type`分别指定DenseGEMM、MOE和KVCache量化类型，缺省时不量化，如`'{"quantization":"mix_quant","dense_quant_type":"wint8","moe_quant_type":"wint4","kv_cache_quant_type":"block_wise_fp8"}'`，注：仅AppendAttn后端支持KVCache在线量化`block_wise_fp8` |
 | ```gpu_memory_utilization```       | `float`     | GPU显存利用率，默认0.9 |
 | ```num_gpu_blocks_override```      | `int`       | 预分配KVCache块数，此参数可由FastDeploy自动根据显存情况计算，无需用户配置，默认为None |
 | ```max_num_batched_tokens```       | `int`       | Prefill阶段最大Batch的Token数量，默认为None(与max_model_len一致) |