gahow/agentic-kvc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add vLLM v0.18.1 source tree with KV transfer abort fix

Browse Source 
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:

  vllm/v1/core/sched/scheduler.py:
    Replace fatal assert with graceful skip when KV transfer callback
    arrives for an already-aborted request during PD disaggregated serving.

Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Gahow Wang
2026-05-22 00:30:38 +08:00
parent b6591950bc
commit 445e491123
4285 changed files with 1111303 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
third_party/vllm/tests/models/fixtures/audioflamingo3/expected_results_batched.json vendored Normal file
View File

@@ -0,0 +1 @@
{"transcriptions": ["There is no clear relationship between the barking and the music, as they seem to be independent of each other.", "(B) To indicate that language cannot express clearly, satirizing the inversion of black and white in the world"], "token_ids": [[3862, 374, 902, 2797, 5025, 1948, 279, 293, 33452, 323, 279, 4627, 11, 438, 807, 2803, 311, 387, 9489, 315, 1817, 1008, 13, 151645], [5349, 8, 2014, 13216, 429, 4128, 4157, 3158, 9355, 11, 7578, 404, 4849, 279, 46488, 315, 3691, 323, 4158, 304, 279, 1879, 151645, 151671]]}

1
third_party/vllm/tests/models/fixtures/audioflamingo3/expected_results_single.json vendored Normal file
View File

@@ -0,0 +1 @@
{"transcriptions": ["The content of the input audio is 'you can ask why over and over and over again forever even if one day we explain every physical interaction and scientific law and hope and dream and regret with a single elegant equation'."], "token_ids": [[785, 2213, 315, 279, 1946, 7699, 374, 364, 9330, 646, 2548, 3170, 916, 323, 916, 323, 916, 1549, 15683, 1496, 421, 825, 1899, 582, 10339, 1449, 6961, 16230, 323, 12344, 2329, 323, 3900, 323, 7904, 323, 22231, 448, 264, 3175, 25777, 23606, 4427, 151645]]}

1
third_party/vllm/tests/models/fixtures/mistral_small_3_chat.json vendored Normal file
View File

File diff suppressed because one or more lines are too long

1
third_party/vllm/tests/models/fixtures/pixtral_chat.json vendored Normal file
View File

File diff suppressed because one or more lines are too long

1
third_party/vllm/tests/models/fixtures/qwen2_5_math_prm_reward_step.json vendored Normal file
View File

@@ -0,0 +1 @@
[[[0.0006361007690429688, 0.99951171875], [0.81884765625, 0.1812744140625], [0.025543212890625, 0.974609375], [0.0004382133483886719, 0.99951171875]]]