[Bugfix] Fix structured outputs errors: TypeError: apply_token_bitmask_inplace_cpu() (#6151)
### What this PR does / why we need it? Fix https://github.com/vllm-project/vllm-ascend/issues/5524 - vLLM version: v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/d68209402ddab3f54a09bc1f4de9a9495a283b60 Signed-off-by: wjunLu <wjunlu217@gmail.com>
This commit is contained in:
1 parent
08a45e6053
commit
72ffc00b86
3 files changed
+3
-2
No files matched your search
@@ -99,8 +99,7 @@ jobs:
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_camem.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_completion_with_prompt_embeds.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_cpu_offloading.py
|
||||
# xgrammar has parameter mismatching bug, please follows: https://github.com/vllm-project/vllm-ascend/issues/5524
|
||||
# pytest -sv --durations=0 tests/e2e/singlecard/test_guided_decoding.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_guided_decoding.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_ilama_lora.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_llama32_lora.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_qwen3_multi_loras.py
|
||||
|
||||
@@ -25,6 +25,7 @@ requires = [
|
||||
"msgpack",
|
||||
"quart",
|
||||
"numba",
|
||||
"xgrammar>=0.1.30",
|
||||
"fastapi<0.124.0",
|
||||
"opencv-python-headless<=4.11.0.86", # Required to avoid numpy version conflict with vllm
|
||||
"compressed_tensors>=0.11.0",
|
||||
|
||||
@@ -14,6 +14,7 @@ setuptools-scm>=8
|
||||
torch==2.9.0
|
||||
torchvision
|
||||
wheel
|
||||
xgrammar>=0.1.30
|
||||
pandas-stubs
|
||||
opencv-python-headless<=4.11.0.86 # Required to avoid numpy version conflict with vllm
|
||||
compressed_tensors>=0.11.0
|
||||
|
||||
Reference in new issue
Block a user