apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Bug fix] Fix block num in scheduler v1 for release2.0.4 (#3314)

Browse Source 
* fix bug for scheduler v0

* fix block num setting in scheduler v1

* fix block num setting in scheduler v1

* fix block num setting in scheduler v1

* fix block num setting in scheduler v1

* fix block num setting in scheduler v1
This commit is contained in:
chenjian
2025-08-11 23:55:45 +08:00
committed by GitHub
parent 4646aff25c
commit c6a133d573
5 changed files with 34 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/worker/gpu_model_runner.py
View File

@@ -208,11 +208,15 @@ class GPUModelRunner(ModelRunnerBase):
request = req_dicts[i]
idx = request.idx
if request.task_type.value == RequestType.PREFILL.value: # prefill task
logger.debug(f"Handle prefill request {request} at idx {idx}")
prefill_start_index = request.prefill_start_index
prefill_end_index = request.prefill_end_index
length = prefill_end_index - prefill_start_index
input_ids = request.prompt_token_ids + request.output_token_ids
logger.debug(
f"Handle prefill request {request} at idx {idx}, "
f"{prefill_start_index=}, {prefill_end_index=}, "
f"need_prefilled_token_num={len(input_ids)}"
)
self.share_inputs["input_ids"][idx : idx + 1, :length] = np.array(
input_ids[prefill_start_index:prefill_end_index]
)