Harry MellorandGitHub b6dd32aa07 Make name of compressed-tensors quant method consistent across vLLM (#17255) ...

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2025-04-28 16:28:13 +00:00

..

piecewise

Support FIPS enabled machines with MD5 hashing (#15299)

2025-03-26 20:19:46 -04:00

__init__.py

[torch.compile] register allreduce operations as custom ops (#8526)

2024-09-16 22:57:57 -07:00

backend.py

Update to torch==2.6.0 (#12721)

2025-03-14 16:58:30 -04:00

conftest.py

[V1] V1 Enablement Oracle (#13726)

2025-03-14 22:02:20 -07:00

test_basic_correctness.py

[Core] Update dtype detection and defaults (#14858)

2025-03-19 13:49:33 +08:00

test_full_graph.py

Make name of compressed-tensors quant method consistent across vLLM (#17255)

2025-04-28 16:28:13 +00:00

test_functionalization.py

[Feature] support sequence parallelism using compilation pass (#16155)

2025-04-27 06:29:35 -07:00

test_fusion.py

[Feature] support sequence parallelism using compilation pass (#16155)

2025-04-27 06:29:35 -07:00

test_pass_manager.py

[Feature] support sequence parallelism using compilation pass (#16155)

2025-04-27 06:29:35 -07:00

test_sequence_parallelism.py

[Feature] support sequence parallelism using compilation pass (#16155)

2025-04-27 06:29:35 -07:00

test_wrapper.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00