Fangzhou AiandCursor 04c1f4a407 [Bugfix][ROCm][DSv4.1] Disable SWA bounded replay on ROCm (#57906) ...

Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

2026-09-21 10:29:14 +00:00

..

amd

[ROCm][DSv4.1] Keep the Engram tables in host memory on ROCm (#57491)

2026-09-21 10:17:11 +08:00

common

[DSV4.1] Add encoder cuda graph support for deepseek-v4.1-flash (#56625)

2026-09-20 21:51:13 +08:00

nvidia

[Model][Engram] Share host tables across co-located DP replicas by default (#57651)

2026-09-21 08:26:56 +00:00

__init__.py

[Refactor] Normalize DeepSeek V4.1 model package naming (#56741)

2026-09-13 23:17:50 -07:00

attention.py

[Bugfix][ROCm][DSv4.1] Disable SWA bounded replay on ROCm (#57906)

2026-09-21 10:29:14 +00:00

compressor.py

[Refactor] Normalize DeepSeek V4.1 model package naming (#56741)

2026-09-13 23:17:50 -07:00

quant_config.py

[Refactor] Normalize DeepSeek V4.1 model package naming (#56741)

2026-09-13 23:17:50 -07:00

sparse_mla.py

[Feat][Model] Support encoder-side SWA-bounded replay for DeepSeek-V4.1-Flash (#56227)

2026-09-18 15:01:24 -07:00