Ye (Charlotte) Qi a100152288 [Kernels][FI] Skip trtllm attention when num_kv_heads=1 (#30842) ...

Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>

2025-12-17 01:54:21 -08:00

..

__init__.py

[Misc] Remove redundant attention var constants (#29650)

2025-11-28 04:35:19 -08:00

argparse_utils.py

[Frontend] Remove confusing -O.xx flag error (#30169)

2025-12-07 02:53:42 +00:00

async_utils.py

[mypy] Pass type checking for vllm/utils and vllm/v1/pool (#29666)

2025-11-28 20:40:47 +08:00

cache.py

[Docs] Mock all imports for docs (#27873)

2025-11-01 10:02:23 +00:00

collection_utils.py

[Misc] Remove redundant ClassRegistry (#29681)

2025-11-28 15:24:47 -08:00

counter.py

[Misc] Separate out utils.counter and move utils.Device to engine (#27588)

2025-10-28 12:20:46 +00:00

deep_gemm.py

[Bugfix] Fix fusion for VL models (#30244)

2025-12-14 21:22:37 +08:00

flashinfer.py

[Kernels][FI] Skip trtllm attention when num_kv_heads=1 (#30842)

2025-12-17 01:54:21 -08:00

func_utils.py

[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)

2025-10-19 05:20:55 -07:00

gc_utils.py

[Doc]: fixing typos in multiple files. (#29685)

2025-11-28 08:41:41 -08:00

hashing.py

[Core] Add xxHash as a high-performance hash option for accelerating prefix caching (#29163)

2025-12-03 16:06:57 +00:00

import_utils.py

[Build] Add OpenAI triton_kernels (#28788)

2025-11-18 16:45:20 -08:00

jsontree.py

[mypy] Pass type checking for vllm/utils and vllm/v1/pool (#29666)

2025-11-28 20:40:47 +08:00

math_utils.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

mem_constants.py

[Chore] Separate out vllm.utils.mem_utils (#27143)

2025-10-18 10:06:59 +00:00

mem_utils.py

[mypy] Pass type checking for vllm/utils and vllm/v1/pool (#29666)

2025-11-28 20:40:47 +08:00

nccl.py

[mypy] Pass type checking for vllm/utils and vllm/v1/pool (#29666)

2025-11-28 20:40:47 +08:00

network_utils.py

[mypy] Pass type checking for vllm/utils and vllm/v1/pool (#29666)

2025-11-28 20:40:47 +08:00

nvtx_pytorch_hooks.py

[Feature] Add Layer-wise NVTX Support (#29990)

2025-12-05 11:20:07 +00:00

platform_utils.py

[BugFix][ROCm] Fix get_cu_count missing variable error (#28608)

2025-11-13 05:18:56 +00:00

profiling.py

[Chore] Separate out profiling utilities from vllm.utils (#27150)

2025-10-18 19:12:01 +00:00

registry.py

[mypy] Pass type checking for vllm/utils and vllm/v1/pool (#29666)

2025-11-28 20:40:47 +08:00

serial_utils.py

[Frontend] Binary embedding response does not return metadata by setting encoding_format to bytes_only. (#30249)

2025-12-08 12:01:21 +00:00

system_utils.py

[Bugfix] Respect VLLM_CONFIGURE_LOGGING value (#28671)

2025-12-03 22:00:52 +00:00

tensor_schema.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

torch_utils.py

Revert "[Fix]Load kv-cache dtype from hf_quant_config.json automatically" (#30653)

2025-12-14 19:33:41 -05:00