Adrian Abeyta c42ff4f4fd

[BugFix][torch.compile] KV scale calculation issues with FP8 quantization (#25513) ...

Signed-off-by: adabeyta <aabeyta@redhat.com>

2025-09-29 15:52:04 -04:00

..

backends

[torch.compile] Make Query Quantization Fusable (#24914)

2025-09-25 09:25:12 -04:00

layers

Directly get max encoder len from VLLM config in V1 (#24866)

2025-09-16 17:52:31 +00:00

ops

[Misc] fix tests failure by using current_platform (#25825)

2025-09-29 04:18:57 +00:00

utils

[Attention] FlashAttn MLA (#14258)

2025-09-04 02:47:59 -07:00

__init__.py

[V0 Deprecation] Remove unused classes in attention (#25541)

2025-09-24 13:24:40 -07:00

layer.py

[BugFix][torch.compile] KV scale calculation issues with FP8 quantization (#25513)

2025-09-29 15:52:04 -04:00

selector.py

[V0 deprecation] Remove _VLLM_V1 suffixes from attention backend names (#25489)

2025-09-25 17:37:50 +00:00