Woosuk Kwon 2863befce3

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

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

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

..

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

[TPU] support attention head dim smaller than 128 (#19620)

2025-06-16 06:40:53 +00:00

test_kv_cache_update_kernel.py

[TPU] add kv cache update kernel (#19928)

2025-06-26 10:01:37 -07:00

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] add kv cache update kernel (#19928)

2025-06-26 10:01:37 -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

[TPU] Skip hanging tests (#19115)

2025-06-04 01:43:00 -07:00

test_topk_topp_sampler.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

test_tpu_qkv_linear.py

[Hardware][TPU] Initial support of model parallelism with single worker using SPMD (#18011)

2025-06-03 00:06:20 +00:00