XiongfeiWeiandGitHub d4170fad39 Use w8a8 quantized matmul Pallas kernel (#19170) ...

Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>

2025-07-15 03:06:33 +00:00

..

worker

[Optimization] Use Shared CachedRequestData Instance Across All Requests (#20232)

2025-06-30 09:07:50 -07:00

__init__.py

[V1] TPU - Add tensor parallel support via Ray (#13618)

2025-03-08 08:19:38 -05:00

test_basic.py

Use w8a8 quantized matmul Pallas kernel (#19170)

2025-07-15 03:06:33 +00:00

test_kv_cache_update_kernel.py

[TPU] kv cache update kernel supports dynamic grid (#20235)

2025-07-02 06:33:37 +00:00

test_mha_attn.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_multimodal.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_pallas.py

[TPU][Bugfix] fix test_pallas (#20666)

2025-07-09 09:32:48 -07:00

test_perf.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_sampler.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_spmd_model_weight_loading.py

[Misc] Add SPDX-FileCopyrightText (#20428)

2025-07-04 07:40:42 +00:00

test_topk_topp_sampler.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_tpu_qkv_linear.py

[Misc] Add SPDX-FileCopyrightText (#20428)

2025-07-04 07:40:42 +00:00