Shiyang Chen e7b41b7823 inline _install_kpool_cache_hooks ...

Signed-off-by: Shiyang Chen <shiychen@nvidia.com>

2026-09-30 14:56:19 -07:00

..

_test_utils

Limit indexer K-cache fake quantization to DeepSeek-V4 and GLM-5.3-Flash

2026-09-30 11:13:59 -07:00

examples

[4/5] Add the IQ2_S CUDA encoder and register the format (#2565)

2026-09-29 20:35:38 +00:00

gpu

[4/5] Add the IQ2_S CUDA encoder and register the format (#2565)

2026-09-29 20:35:38 +00:00

gpu_megatron

Add fake quantization of the sparse-attention indexer query

2026-09-30 12:09:07 -07:00

gpu_trtllm

Fix 2-GPU test_model_load_utils hang; test import and fixture cleanup (#2079)

2026-08-05 21:00:42 +05:30

gpu_vllm

inline _install_kpool_cache_hooks

2026-09-30 14:56:19 -07:00

regression/torch/speculative

Speed up slow unit/gpu/example tests (#1616)

2026-06-04 17:13:10 +00:00

unit

Add fake quantization of the sparse-attention indexer query

2026-09-30 12:09:07 -07:00

conftest.py

[1/2] One MLflow tracking core behind a Tool record (#2544)

2026-09-28 19:57:03 +00:00