20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[TPU] [V1] fix cases when max_num_reqs is set smaller than MIN_NUM_SEQS (#15583)

Browse Source 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
This commit is contained in:
Chengji Yao 2025-03-26 22:46:26 -07:00 committed by GitHub
parent ecff8309a3
commit 619d3de8bd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/offline_inference/tpu.py
View File

@ -14,10 +14,7 @@ answers = [
]
N = 1
# Currently, top-p sampling is disabled. `top_p` should be 1.0.
sampling_params = SamplingParams(temperature=0.7,
top_p=1.0,
n=N,
max_tokens=16)
sampling_params = SamplingParams(temperature=0, top_p=1.0, n=N, max_tokens=16)
# Set `enforce_eager=True` to avoid ahead-of-time compilation.
# In real workloads, `enforace_eager` should be `False`.

2
vllm/v1/worker/tpu_model_runner.py
View File

@ -88,7 +88,7 @@ class TPUModelRunner:
self.max_model_len = model_config.max_model_len
self.max_num_blocks_per_req = cdiv(self.max_model_len, self.block_size)
self.max_num_tokens = scheduler_config.max_num_batched_tokens
self.max_num_reqs = scheduler_config.max_num_seqs
self.max_num_reqs = max(scheduler_config.max_num_seqs, MIN_NUM_SEQS)
# Model-related.
self.num_attn_layers = model_config.get_num_layers_by_block_type(