Longzhi Wang 2eea6fa97a [BugFix] Fix kv cache int8 dynamic quant on flash and flash_mask backend (#7028) ...

* [BugFix] Fix kv cache int8 dynamic quant on flash and flash_mask backend

* add constexpr and code style clean

* add test

* fix code style

* fix test

2026-03-30 11:17:15 +08:00

..

graph_optimization

[Speculative Decoding] Unify Spec and non-spec branch (#6685)

2026-03-10 23:58:44 -07:00

guided_decoding

[Optimization] Use a separate driver when using Triton with Paddle (#6897)

2026-03-24 10:56:00 +08:00

layers

[BugFix] Fix kv cache int8 dynamic quant on flash and flash_mask backend (#7028)

2026-03-30 11:17:15 +08:00

logits_processor

[Bugfix] Align thinking_budget behavior with ERNIE reasoning flow (#6934)

2026-03-23 14:15:55 +08:00

model_loader

add reconstruct (#6675)

2026-03-10 11:25:37 +08:00

models

[Optimization] Use a separate driver when using Triton with Paddle (#6897)

2026-03-24 10:56:00 +08:00

ops

[Optimization] Use a separate driver when using Triton with Paddle (#6897)

2026-03-24 10:56:00 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

entropy_utils.py

[Bugfix] Fix entropy calculation bugs (#5941)

2026-01-08 20:57:35 +08:00

forward_meta.py

[Other] Adjust GPUModelRunner to enhance compatibility (#6851)

2026-03-16 14:49:19 +08:00

load_weight_utils.py

add reconstruct (#6675)

2026-03-10 11:25:37 +08:00

pre_and_post_process.py

[Speculative Decoding] Optimize attn_mask_offset and fix mtp bug (#7005)

2026-03-25 01:52:06 -07:00

utils.py

[BugFix][Optimization] Replace silent failures with catchable exceptions and informative error messages (#6533)

2026-03-16 21:32:43 +08:00

xpu_pre_and_post_process.py

[XPU] rm stop nums (#6651)

2026-03-12 14:05:58 +08:00