Jiangyun ZhuandOpenAI Codex 20b52e9f5b [Perf][Qwen3.8] Reduce PLE metadata construction overhead (#58114) ...

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-09-28 20:46:22 +08:00

..

__init__.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_config.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_hc_ops.py

[Perf][Qwen4Exp] Fuse HC down projection and SiLU on NVIDIA (#58957)

2026-09-28 18:51:38 +08:00

test_ple.py

[Perf][Qwen3.8] Reduce PLE metadata construction overhead (#58114)

2026-09-28 20:46:22 +08:00

test_qsa_amd.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_qsa_pre_indexer.py

[Qwen3.8-Flash-Next] Support FP8 indexer cache for QSA (#54890)

2026-09-07 12:15:45 +00:00

test_qsa_reference.py

[Bugfix][Qwen4Exp] Release the profiling KV cache held by QSA key views (#58961)

2026-09-28 08:11:46 +00:00