[Clean] Remove deprecated environs (#21536)

python/sglang/srt/environ.py

@@ -337,9 +337,7 @@ class Envs:
 
     # Flashinfer
     SGLANG_IS_FLASHINFER_AVAILABLE = EnvBool(True)
-    SGLANG_ENABLE_FLASHINFER_FP8_GEMM = EnvBool(False)
     # Default to the pick from flashinfer
-    SGLANG_FLASHINFER_FP4_GEMM_BACKEND = EnvStr("")
     SGLANG_FLASHINFER_WORKSPACE_SIZE = EnvInt(384 * 1024 * 1024)
     # TODO(mmangkad): Remove this once the FlashInfer unified allreduce-fusion
     # transport issue on GB200/GB300 platforms is fixed and verified resolved.
@@ -408,7 +406,6 @@ class Envs:
     DISABLE_OPENAPI_DOC = EnvBool(False)
     SGLANG_ENABLE_TORCH_INFERENCE_MODE = EnvBool(False)
     SGLANG_IS_FIRST_RANK_ON_NODE = EnvBool(True)
-    SGLANG_SUPPORT_CUTLASS_BLOCK_FP8 = EnvBool(False)
     SGLANG_SYNC_TOKEN_IDS_ACROSS_TP = EnvBool(False)
     SGLANG_ENABLE_COLOCATED_BATCH_GEN = EnvBool(False)
 
@@ -548,9 +545,6 @@ def _warn_deprecated_env_to_cli_flag(env_name: str, suggestion: str):
 
 def _convert_SGL_to_SGLANG():
     _print_deprecated_env("SGLANG_LOG_GC", "SGLANG_GC_LOG")
-    _print_deprecated_env(
-        "SGLANG_ENABLE_FLASHINFER_FP8_GEMM", "SGLANG_ENABLE_FLASHINFER_GEMM"
-    )
     _print_deprecated_env(
         "SGLANG_MOE_NVFP4_DISPATCH", "SGLANG_CUTEDSL_MOE_NVFP4_DISPATCH"
     )
@@ -581,23 +575,6 @@ def _convert_SGL_to_SGLANG():
 
 
 _convert_SGL_to_SGLANG()
-
-_warn_deprecated_env_to_cli_flag(
-    "SGLANG_ENABLE_FLASHINFER_FP8_GEMM",
-    "It will be completely removed in 0.5.7. Please use '--fp8-gemm-backend=flashinfer_trtllm' instead.",
-)
-_warn_deprecated_env_to_cli_flag(
-    "SGLANG_ENABLE_FLASHINFER_GEMM",
-    "It will be completely removed in 0.5.7. Please use '--fp8-gemm-backend=flashinfer_trtllm' instead.",
-)
-_warn_deprecated_env_to_cli_flag(
-    "SGLANG_SUPPORT_CUTLASS_BLOCK_FP8",
-    "It will be completely removed in 0.5.7. Please use '--fp8-gemm-backend=cutlass' instead.",
-)
-_warn_deprecated_env_to_cli_flag(
-    "SGLANG_FLASHINFER_FP4_GEMM_BACKEND",
-    "It will be completely removed in 0.5.9. Please use '--fp4-gemm-backend' instead.",
-)
 _warn_deprecated_env_to_cli_flag(
     "SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE",
     "Please use '--enable-prefill-delayer' instead.",

python/sglang/srt/layers/quantization/fp4_utils.py

@@ -4,7 +4,6 @@ import logging
 from enum import Enum
 from typing import TYPE_CHECKING
 
-from sglang.srt.environ import envs
 from sglang.srt.utils.common import is_sm120_supported
 
 if TYPE_CHECKING:
@@ -56,26 +55,6 @@ def initialize_fp4_gemm_config(server_args: ServerArgs) -> None:
     global FP4_GEMM_RUNNER_BACKEND
 
     backend = server_args.fp4_gemm_runner_backend
-
-    # Handle deprecated env var for backward compatibility
-    # TODO: Remove this in a future version
-    if envs.SGLANG_FLASHINFER_FP4_GEMM_BACKEND.is_set():
-        env_backend = envs.SGLANG_FLASHINFER_FP4_GEMM_BACKEND.get()
-        if backend == "auto":
-            logger.warning(
-                "SGLANG_FLASHINFER_FP4_GEMM_BACKEND is deprecated. "
-                f"Please use '--fp4-gemm-backend={env_backend}' instead."
-            )
-            if not env_backend.startswith("flashinfer_"):
-                env_backend = "flashinfer_" + env_backend
-            backend = env_backend
-        else:
-            logger.warning(
-                f"FP4 GEMM backend set to '{backend}' via --fp4-gemm-backend overrides "
-                "environment variable SGLANG_FLASHINFER_FP4_GEMM_BACKEND. "
-                "Using server argument value."
-            )
-
     if backend == "auto":
         if is_sm120_supported():
             # flashinfer_cutlass produces NaN in dense MLP layers with

python/sglang/srt/layers/quantization/fp8_utils.py

@@ -7,7 +7,6 @@ from typing import TYPE_CHECKING, Callable, List, Optional, Tuple
 
 import torch
 
-from sglang.srt.environ import envs
 from sglang.srt.layers import deep_gemm_wrapper
 from sglang.srt.layers.quantization.fp8_kernel import sglang_per_token_group_quant_fp8
 from sglang.srt.layers.quantization.mxfp4_tensor import MXFP4QuantizeUtil
@@ -453,25 +452,6 @@ def initialize_fp8_gemm_config(server_args: ServerArgs) -> None:
     global FP8_GEMM_RUNNER_BACKEND
 
     backend = server_args.fp8_gemm_runner_backend
-
-    # TODO(brayden): Remove env-based overrides in v0.5.7, they will be fully removed in v0.5.7.
-    # Only check environment variables when the server args is not set, server args should take priority.
-    if backend == "auto":
-        if envs.SGLANG_ENABLE_FLASHINFER_FP8_GEMM.get():
-            backend = "flashinfer_trtllm"
-        elif envs.SGLANG_SUPPORT_CUTLASS_BLOCK_FP8.get():
-            backend = "cutlass"
-    else:
-        if (
-            envs.SGLANG_ENABLE_FLASHINFER_FP8_GEMM.get()
-            or envs.SGLANG_SUPPORT_CUTLASS_BLOCK_FP8.get()
-        ):
-            logger.warning(
-                f"FP8 GEMM backend set to '{backend}' via --fp8-gemm-backend overrides "
-                "environment variables SGLANG_ENABLE_FLASHINFER_FP8_GEMM and "
-                "SGLANG_SUPPORT_CUTLASS_BLOCK_FP8. Using server argument value."
-            )
-
     if backend == "auto" and is_sm120_supported():
         # TODO(brayden): Verify if CUTLASS can be set by default once SwapAB is supported
         backend = "triton"

python/sglang/srt/server_args.py

@@ -4632,9 +4632,7 @@ class ServerArgs:
             "'flashinfer_deepgemm' (Hopper SM90 only; uses swapAB optimization for small M dimensions in decoding), "
             "'cutlass' (optimal for Hopper/Blackwell GPUs and high-throughput), "
             "'triton' (fallback, widely compatible), "
-            "'aiter' (ROCm only). "
-            "NOTE: This replaces the deprecated environment variables "
-            "SGLANG_ENABLE_FLASHINFER_FP8_GEMM and SGLANG_SUPPORT_CUTLASS_BLOCK_FP8.",
+            "'aiter' (ROCm only). ",
         )
         parser.add_argument(
             "--fp4-gemm-backend",
@@ -4646,9 +4644,7 @@ class ServerArgs:
             "Options: 'auto' (default; selects flashinfer_cudnn on SM120, flashinfer_cutlass otherwise), "
             "'flashinfer_cutlass' (CUTLASS backend), "
             "'flashinfer_cudnn' (FlashInfer cuDNN backend, optimal on CUDA 13+ with cuDNN 9.15+), "
-            "'flashinfer_trtllm' (FlashInfer TensorRT-LLM backend, requires different weight preparation with shuffling). "
-            "NOTE: This replaces the deprecated environment variable "
-            "SGLANG_FLASHINFER_FP4_GEMM_BACKEND.",
+            "'flashinfer_trtllm' (FlashInfer TensorRT-LLM backend, requires different weight preparation with shuffling). ",
         )
         parser.add_argument(
             "--disable-flashinfer-autotune",