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

[Fix] Add speculative_draft_model_revision to server_args (#5255)

Browse Source 
Signed-off-by: Devashish Lal <devashish@rivosinc.com>
This commit is contained in:
DevashishLal-CB
2025-09-05 04:45:46 -07:00
committed by GitHub
parent df97b31f37
commit 13705dae06
13 changed files with 68 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
benchmark/gpt_oss/README.md
View File

@@ -132,8 +132,8 @@ python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algori
# On Blackwell:
# - Chain decoding (topk = 1) is supported on TRTLLM-MHA backend. Tree decoding (topk > 1) is in progress, stay tuned!
# - Both tree decoding (topk > 1) and chain decoding (topk = 1) are supported on the Triton backend.
python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algo EAGLE3 --speculative-draft lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --tp 4
python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algo EAGLE3 --speculative-draft lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 5 --speculative-eagle-topk 4 --speculative-num-draft-tokens 8 --attention-backend triton --tp 4
python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algo EAGLE3 --speculative-draft-model-path lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --tp 4
python3 -m sglang.launch_server --model openai/gpt-oss-120b --speculative-algo EAGLE3 --speculative-draft-model-path lmsys/EAGLE3-gpt-oss-120b-bf16 --speculative-num-steps 5 --speculative-eagle-topk 4 --speculative-num-draft-tokens 8 --attention-backend triton --tp 4
```
Benchmark Command

2
benchmark/mtbench/README.md
View File

@@ -18,7 +18,7 @@ python3 bench_sglang.py --num-questions 80
### Benchmark sglang EAGLE
```
python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3-8B-Instruct --speculative-algo EAGLE \
--speculative-draft lmsys/sglang-EAGLE-LLaMA3-Instruct-8B --speculative-num-steps 5 \
--speculative-draft-model-path lmsys/sglang-EAGLE-LLaMA3-Instruct-8B --speculative-num-steps 5 \
--speculative-eagle-topk 8 --speculative-num-draft-tokens 64 --dtype float16 --port 30000
```