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

Fix input_ids && rename to fill_ids (#1021)

Browse Source
This commit is contained in:
Liangsheng Yin
2024-08-10 16:24:12 -07:00
committed by GitHub
parent 54fb1c80c0
commit 43fbb6d919
7 changed files with 28 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
python/sglang/bench_latency.py
View File

@@ -152,7 +152,7 @@ def prepare_inputs_for_correctness_test(bench_args, tokenizer):
req = Req(rid=i, origin_input_text=prompts[i], origin_input_ids=tmp_input_ids)
req.prefix_indices = []
req.sampling_params = sampling_params
req.input_ids = req.origin_input_ids
req.fill_ids = req.origin_input_ids
reqs.append(req)
return input_ids, reqs
@@ -163,7 +163,7 @@ def prepare_extend_inputs_for_correctness_test(
):
for i in range(len(reqs)):
req = reqs[i]
req.input_ids += input_ids[i][bench_args.cut_len :]
req.fill_ids += input_ids[i][bench_args.cut_len :]
req.prefix_indices = model_runner.req_to_token_pool.req_to_token[
i, : bench_args.cut_len
]
@@ -182,7 +182,7 @@ def prepare_synthetic_inputs_for_latency_test(batch_size, input_len):
req = Req(rid=i, origin_input_text="", origin_input_ids=list(input_ids[i]))
req.prefix_indices = []
req.sampling_params = sampling_params
req.input_ids = req.origin_input_ids
req.fill_ids = req.origin_input_ids
reqs.append(req)
return reqs