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

[P/D] NIXL Integration (#17751)

Browse Source 
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Brent Salisbury <bsalisbu@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Brent Salisbury <bsalisbu@redhat.com>
This commit is contained in:
Robert Shaw
2025-05-12 12:46:16 -04:00
committed by GitHub
parent 05a4324f8e
commit d19110204c
34 changed files with 2723 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/v1/core/test_scheduler.py
View File

@@ -870,7 +870,7 @@ def test_kv_connector_basic():
NUM_MATCHED_NEW_TOKENS = BLOCK_SIZE * 2
scheduler.connector.get_num_new_matched_tokens = Mock(name="method")
scheduler.connector.get_num_new_matched_tokens.return_value = (
NUM_MATCHED_NEW_TOKENS)
NUM_MATCHED_NEW_TOKENS, False)
######################################################
# FIRST SET OF REQUESTS - External Hit Only
@@ -981,7 +981,7 @@ def test_kv_connector_unable_to_allocate():
NUM_MATCHED_NEW_TOKENS = BLOCK_SIZE * 2
scheduler.connector.get_num_new_matched_tokens = Mock(name="method")
scheduler.connector.get_num_new_matched_tokens.return_value = (
NUM_MATCHED_NEW_TOKENS)
NUM_MATCHED_NEW_TOKENS, False)
# Create two requests. The second request will not be able to
# allocate slots because it will not have enough blocks.
@@ -1060,7 +1060,7 @@ def test_kv_connector_handles_preemption():
NUM_MATCHED_NEW_TOKENS = BLOCK_SIZE
scheduler.connector.get_num_new_matched_tokens = Mock(name="method")
scheduler.connector.get_num_new_matched_tokens.return_value = (
NUM_MATCHED_NEW_TOKENS)
NUM_MATCHED_NEW_TOKENS, False)
# Create two requests.
# Both can be scheduled at first, but the second request