Wei-Ming Chen 5b02483c5f AWQ support for vllm fake quant (dense model) (#409) ...

Signed-off-by: weimingc <17592131+meenchen@users.noreply.github.com>

2025-10-09 12:00:49 -07:00

..

_deploy

Specify engine path for TRT evaluation (#313)

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

distill

Allow passing in DistillationConfig directly to setup fn (#399)

2025-10-02 19:42:42 +00:00

export

Fix: supporting gpt-oss HF eagle (#398)

2025-10-09 01:14:00 +00:00

nas

Remove unnecessary Tracing use in Minitron Search Space generation (#405)

2025-10-08 09:38:13 +05:30

opt

Fix multi-gpu mamba minitron param sorting test + minor cleanup (#412)

2025-10-08 22:09:53 +05:30

peft

[1/N] ModelOPT PEFT mode support for the megatron-lm (#342)

2025-10-09 01:36:22 +00:00

prune

Remove unnecessary Tracing use in Minitron Search Space generation (#405)

2025-10-08 09:38:13 +05:30

quantization

AWQ support for vllm fake quant (dense model) (#409)

2025-10-09 12:00:49 -07:00

sparsity

Code quality improvements - typos, formatting, etc.

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

speculative

Fix: supporting gpt-oss HF eagle (#398)

2025-10-09 01:14:00 +00:00

trace

Remove unnecessary Tracing use in Minitron Search Space generation (#405)

2025-10-08 09:38:13 +05:30

utils

[1/N] ModelOPT PEFT mode support for the megatron-lm (#342)

2025-10-09 01:36:22 +00:00

__init__.py

[1/N] ModelOPT PEFT mode support for the megatron-lm (#342)

2025-10-09 01:36:22 +00:00