[quant] Ignore FP8 quantization layers (#20340)

Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

python/sglang/srt/environ.py

@@ -333,6 +333,7 @@ class Envs:
     SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2 = EnvBool(False)
     SGLANG_NVFP4_CKPT_FP8_NEXTN_MOE = EnvBool(False)
     SGLANG_QUANT_ALLOW_DOWNCASTING = EnvBool(False)
+    SGLANG_FP8_IGNORED_LAYERS = EnvStr("")
 
     # Flashinfer
     SGLANG_IS_FLASHINFER_AVAILABLE = EnvBool(True)

python/sglang/srt/layers/quantization/fp8.py

@@ -131,6 +131,14 @@ class Fp8Config(QuantizationConfig):
             raise ValueError(f"Unsupported activation scheme {activation_scheme}")
         self.activation_scheme = activation_scheme
         self.ignored_layers = ignored_layers or []
+        if ignored_layers_str := envs.SGLANG_FP8_IGNORED_LAYERS.get():
+            self.ignored_layers.extend(
+                [
+                    layer.strip()
+                    for layer in ignored_layers_str.split(",")
+                    if layer.strip()
+                ]
+            )
         self.packed_modules_mapping = packed_modules_mapping or {}
         self.use_mxfp8 = use_mxfp8
         if weight_block_size is not None: