[Misc]Register and refactor some environs for dpsk-fp4 and DeepEp (#14538)

docs/references/environment_variables.md

@@ -55,7 +55,9 @@ SGLang supports various environment variables that can be used to configure its
 | Environment Variable | Description | Default Value |
 | --- | --- | --- |
 | `SGLANG_DEEPEP_BF16_DISPATCH` | Use Bfloat16 for dispatch | `"false"` |
-| `SGLANG_MOE_NVFP4_DISPATCH` | Use nvfp4 for moe dispatch | `"false"` |
+| `SGLANG_MOE_NVFP4_DISPATCH` | Use nvfp4 for moe dispatch (on flashinfer_cutlass or flashinfer_cutedsl moe runner backend) | `"false"` |
+| `SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK` | The maximum number of dispatched tokens on each GPU | `"128"` |
+| `SGLANG_DEEPEP_LL_COMBINE_SEND_NUM_SMS` | Number of SMs used for DeepEP combine when single batch overlap is enabled | `"32"` |
 
 ## Memory Management
 
@@ -65,6 +67,8 @@ SGLang supports various environment variables that can be used to configure its
 | `SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION` | Clip max new tokens estimation for memory planning | `4096` |
 | `SGLANG_DETOKENIZER_MAX_STATES` | Maximum states for detokenizer | Default value based on system |
 | `SGL_DISABLE_TP_MEMORY_INBALANCE_CHECK` | Disable checks for memory imbalance across Tensor Parallel ranks | Not set (defaults to enabled check) |
+| `SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN` | Quantize q_b_proj from BF16 to FP8 when launching DeepSeek NVFP4 checkpoint | `false` |
+| `SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2` | Apply per token group quantization kernel with fused silu and mul and masked m | `false` |
 
 ## Model-Specific Options