Mohit SinglaandCodex 613ab20f7f [Model] Enable torch.compile for Sarvam MLA (#55817) ...

Signed-off-by: mohit-sarvam <mohit@sarvam.ai>
Co-authored-by: Codex <noreply@openai.com>

2026-09-08 22:01:30 +08:00

..

determinism

[Docs] Add missing return annotations flagged by griffe (#54980)

2026-09-02 09:56:07 -07:00

hw_agnostic

Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)

2026-08-13 11:21:50 +01:00

kernels

[Perf][Quant][NVFP4] Prefer W4A4 linear kernels over weight-only ones on SM120/121 (#55170)

2026-09-08 15:06:45 +04:00

layers

[Perf][GDN] Enable the FlashInfer GDN prefill kernel on SM12x (#55715)

2026-09-08 12:26:03 +00:00

model_loader

[Quantization] Support online quantization with partially pre-quantized checkpoints (#51392)

2026-09-04 11:46:06 -07:00

models

[Model] Enable torch.compile for Sarvam MLA (#55817)

2026-09-08 22:01:30 +08:00

offloader

[Bugfix][Offloader] Preserve prefetch static-buffer slot ownership (#54975)

2026-09-07 10:58:44 +08:00

warmup

[Bugfix] Autotune FlashInfer deferred MoE decode kernels before CUDA graph capture (#55377)

2026-09-08 04:02:23 +00:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

[Bugfix] Reject contradictory custom-op directives (#49134)

2026-07-26 08:42:14 -04:00

parameter.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

Fast Start (#54921)

2026-09-04 06:32:06 -07:00