EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Misc clean up; Remove the support of jump forward (#4032)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-03-03 07:02:14 -08:00
committed by GitHub
parent 110e006673
commit 935cda944b
41 changed files with 396 additions and 426 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/backend/speculative_decoding.ipynb
View File

@@ -47,7 +47,7 @@
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python3 -m sglang.launch_server --model meta-llama/Llama-2-7b-chat-hf --speculative-algorithm EAGLE \\\n",
" --speculative-draft-model-path lmzheng/sglang-EAGLE-llama2-chat-7B --speculative-num-steps 5 \\\n",
" --speculative-draft-model-path lmsys/sglang-EAGLE-llama2-chat-7B --speculative-num-steps 5 \\\n",
" --speculative-eagle-topk 8 --speculative-num-draft-tokens 64\n",
"\"\"\"\n",
")\n",
@@ -104,7 +104,7 @@
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python3 -m sglang.launch_server --model meta-llama/Llama-2-7b-chat-hf --speculative-algorithm EAGLE \\\n",
" --speculative-draft-model-path lmzheng/sglang-EAGLE-llama2-chat-7B --speculative-num-steps 5 \\\n",
" --speculative-draft-model-path lmsys/sglang-EAGLE-llama2-chat-7B --speculative-num-steps 5 \\\n",
" --speculative-eagle-topk 8 --speculative-num-draft-tokens 64 --mem-fraction 0.6 \\\n",
" --enable-torch-compile --cuda-graph-max-bs 2\n",
"\"\"\"\n",
@@ -175,7 +175,7 @@
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3-8B-Instruct --speculative-algorithm EAGLE \\\n",
" --speculative-draft-model-path lmzheng/sglang-EAGLE-LLaMA3-Instruct-8B --speculative-num-steps 5 \\\n",
" --speculative-draft-model-path lmsys/sglang-EAGLE-LLaMA3-Instruct-8B --speculative-num-steps 5 \\\n",
" --speculative-eagle-topk 8 --speculative-num-draft-tokens 64 --speculative-token-map thunlp/LLaMA3-Instruct-8B-FR-Spec/freq_32768.pt \\\n",
" --mem-fraction 0.7 --cuda-graph-max-bs 2 --dtype float16 \n",
"\"\"\"\n",