biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Deprecate best_of Sampling Parameter in anticipation for vLLM V1 (#13997)

Browse Source 
Signed-off-by: vincent-4 <vincentzhongy+githubvincent4@gmail.com>
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Vincent
2025-03-05 15:22:43 -05:00
committed by GitHub
parent a32c8669ca
commit a4f1ee35d6
12 changed files with 16 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/core/test_scheduler.py
View File

@@ -617,7 +617,6 @@ def test_schedule_decode_blocks_to_copy_update():
num_gpu_blocks=16)
_, seq_group = create_dummy_prompt("1",
prompt_length=60,
best_of=2,
block_size=block_size)
curr_loras = None
scheduler._allocate_and_set_running(seq_group)
@@ -686,7 +685,6 @@ def test_schedule_swapped_cannot_swap_in():
for i in range(2):
_, seq_group = create_dummy_prompt(str(i),
prompt_length=60,
best_of=2,
block_size=block_size)
scheduler._allocate_and_set_running(seq_group)
append_new_token_seq_group(60, seq_group, 1)
@@ -717,7 +715,6 @@ def test_infeasible_swap():
for i in range(2):
_, seq_group = create_dummy_prompt(str(i),
prompt_length=60,
best_of=2,
block_size=block_size)
scheduler._allocate_and_set_running(seq_group)
append_new_token_seq_group(60, seq_group, 1)
@@ -747,7 +744,6 @@ def test_schedule_swapped_blocks_to_copy():
curr_loras = None
_, seq_group = create_dummy_prompt("1",
prompt_length=60,
best_of=2,
block_size=block_size)
scheduler._allocate_and_set_running(seq_group)
append_new_token_seq_group(60, seq_group, 1)