feat: return partial generation results when aborting requests in waiting queue (#11673)

This commit is contained in:
Yuhong Guo
2025-10-29 22:03:00 +08:00
committed by GitHub
parent 750940ae36
commit caa5d2967c
6 changed files with 168 additions and 52 deletions
+1 -1
View File
@@ -71,7 +71,7 @@ suites = {
TestFile("rl/test_fp32_lm_head.py", 30),
TestFile("rl/test_update_weights_from_disk.py", 114),
TestFile("rl/test_update_weights_from_tensor.py", 48),
TestFile("test_abort.py", 51),
TestFile("test_abort.py", 121),
TestFile("test_build_eagle_tree.py", 8),
TestFile("test_chunked_prefill.py", 313),
TestFile("test_create_kvindices.py", 2),