Louie Tsai 006e7a34ae

Adding int4 and int8 models for CPU benchmarking (#23709) ...

Signed-off-by: Tsai, Louie <louie.tsai@intel.com>

2025-09-05 20:08:50 +08:00

..

lm-eval-harness

[Deprecation] Remove prompt_token_ids arg fallback in LLM.generate and LLM.embed (#18800)

2025-08-22 10:56:57 +08:00

nightly-benchmarks

Adding int4 and int8 models for CPU benchmarking (#23709)

2025-09-05 20:08:50 +08:00

scripts

[XPU] support Triton Attention backend on Intel GPU (#24149)

2025-09-04 20:41:08 +08:00

check-wheel-size.py

[Attention] FlashAttn MLA (#14258)

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

generate_index.py

[ci/build] Fix abi tag for aarch64 (#23329)

2025-08-21 23:32:55 +08:00

pyproject.toml

[Doc] Move examples and further reorganize user guide (#18666)

2025-05-26 07:38:04 -07:00

release-pipeline.yaml

Update release pipeline post PyTorch 2.8.0 update (#24073)

2025-09-03 10:09:19 +08:00

test-pipeline.yaml

[Bugfix][Misc] Fix silu_and_mul_nvfp4_quant issue and extract common utils for nvfp4 kernel source files (#23727)

2025-09-04 14:25:45 -07:00