chore: import upstream snapshot with attribution

examples/infer/sglang/demo.sh

@@ -0,0 +1,7 @@
+# test_env: pip install "sglang[all]==0.4.6.*" -U
+CUDA_VISIBLE_DEVICES=0 \
+swift infer \
+    --model Qwen/Qwen2.5-1.5B-Instruct \
+    --infer_backend sglang \
+    --stream true \
+    --max_new_tokens 2048

examples/infer/sglang/distill_qwen3_235b.sh

@@ -0,0 +1,9 @@
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+swift infer \
+    --model Qwen/Qwen3-235B-A22B-Instruct-2507 \
+    --infer_backend sglang \
+    --val_dataset liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT \
+    --sglang_context_length 12000 \
+    --sglang_tp_size 8 \
+    --write_batch_size 10000 \
+    --result_path distill_qwen3_235b.jsonl

examples/infer/sglang/mtp.sh

@@ -0,0 +1,13 @@
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+swift infer \
+    --model ZhipuAI/GLM-4.5-Air \
+    --sglang_tp_size 4 \
+    --infer_backend sglang \
+    --val_dataset AI-ModelScope/alpaca-gpt4-data-zh#100 \
+    --sglang_context_length 8192 \
+    --max_new_tokens 2048 \
+    --sglang_mem_fraction_static 0.7 \
+    --sglang_speculative_algorithm EAGLE \
+    --sglang_speculative_eagle_topk 1 \
+    --sglang_speculative_num_steps 3 \
+    --sglang_speculative_num_draft_tokens 4

examples/infer/sglang/tp.sh

@@ -0,0 +1,9 @@
+CUDA_VISIBLE_DEVICES=0,1 \
+swift infer \
+    --model Qwen/Qwen3-8B \
+    --infer_backend sglang \
+    --val_dataset AI-ModelScope/alpaca-gpt4-data-zh#2000 \
+    --max_new_tokens 2048 \
+    --sglang_context_length 8192 \
+    --sglang_tp_size 2 \
+    --write_batch_size 1000