Chenjie LuoandKeval Morabia ad091e884e Improve realquant gemm impl (#368) ...

Signed-off-by: Chenjie Luo <chenjiel@nvidia.com>
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
Co-authored-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>

2025-09-26 09:37:51 +05:30

..

_deploy

Specify engine path for TRT evaluation (#313)

2025-09-18 13:09:53 -07:00

distill

Copy changes made to Megatron-LM (#372)

2025-09-25 16:51:00 +02:00

export

Slurm support for QAT Simplified Flow + Qwen3-8B recipe (#285)

2025-09-18 11:24:39 -07:00

nas

Support checkpointing Minitron pruning scores / prune without sorting (#361)

2025-09-26 01:46:22 +05:30

opt

Support checkpointing Minitron pruning scores / prune without sorting (#361)

2025-09-26 01:46:22 +05:30

prune

Support checkpointing Minitron pruning scores / prune without sorting (#361)

2025-09-26 01:46:22 +05:30

quantization

Improve realquant gemm impl (#368)

2025-09-26 09:37:51 +05:30

sparsity

Code quality improvements - typos, formatting, etc.

2025-09-02 19:58:33 +05:30

speculative

Feature: Offline training for EAGLE3 (#300)

2025-09-22 23:54:09 +00:00

trace

Code quality improvements - typos, formatting, etc.

2025-09-02 19:58:33 +05:30

utils

[NVBUG: 5472822] Skip memory monitoring if not available (#374)

2025-09-26 09:24:27 +05:30

__init__.py

Update files on Github (#258)

2025-08-17 02:44:16 +05:30