[Feature] Integrate Elastic NIXL-EP into SGLang (#19248)

Signed-off-by: Barak Biber <bbiber@nvidia.com>
Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Co-authored-by: Barak Biber <bbiber@nvidia.com>

python/sglang/srt/environ.py

@@ -271,6 +271,7 @@ class Envs:
     # Override the distributed init method used by torch.distributed.init_process_group.
     # Set to "env://" to use an externally-created TCPStore via MASTER_ADDR/MASTER_PORT.
     SGLANG_DISTRIBUTED_INIT_METHOD_OVERRIDE = EnvStr(None)
+    SGLANG_TCP_STORE_PORT = EnvInt(29600)
 
     # Tool Calling
     SGLANG_FORWARD_UNKNOWN_TOOLS = EnvBool(False)
@@ -378,6 +379,10 @@ class Envs:
     SGLANG_DEEPEP_LL_COMBINE_SEND_NUM_SMS = EnvInt(32)
     SGLANG_BLACKWELL_OVERLAP_SHARED_EXPERTS_OUTSIDE_SBO = EnvBool(False)
 
+    # NIXL-EP
+    SGLANG_NIXL_EP_BF16_DISPATCH = EnvBool(False)
+    SGLANG_NIXL_EP_NUM_MAX_DISPATCH_TOKENS_PER_RANK = EnvInt(128)
+
     # NSA Backend
     SGLANG_NSA_FUSE_TOPK = EnvBool(True)
     SGLANG_NSA_ENABLE_MTP_PRECOMPUTE_METADATA = EnvBool(True)