Nicolò Lucchesi 4cf71cc88a

[TPU] Deprecate xm.mark_step in favor of `torch_xla.sync (#25254) ...

Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>

2025-09-22 10:12:57 +00:00

..

worker

[Core] Use CpuGpuBuffer for block table tensors (#24795)

2025-09-16 19:18:06 -07:00

__init__.py

…

test_basic.py

…

test_kv_cache_update_kernel.py

[TPU] kv cache update kernel doesn't need to be padded slices to multiple of num_slices_per_block (#22394)

2025-08-09 20:49:04 -07:00

test_mha_attn.py

[V0 Deprecation][TPU] Remove V1 flag check from tests (#22248)

2025-08-05 06:53:23 -07:00

test_multimodal.py

[CI/Build] Serve images used by multimodal tests through local HTTP Server (#23907)

2025-09-03 16:13:11 +08:00

test_pallas.py

[Attention][FlashInfer] Enable FP8 FlashInfer (TRTLLM) MLA decode (#24705)

2025-09-12 15:45:53 -06:00

test_perf.py

…

test_sampler.py

[V0 Deprecation][TPU] Remove V1 flag check from tests (#22248)

2025-08-05 06:53:23 -07:00

test_spmd_model_weight_loading.py

…

test_topk_topp_sampler.py

[TPU] Deprecate xm.mark_step in favor of `torch_xla.sync (#25254)

2025-09-22 10:12:57 +00:00

test_tpu_int8.py

[TPU] Add support for online w8a8 quantization (#22425)

2025-08-08 23:12:54 -07:00

test_tpu_qkv_linear.py

…