Skip to content

Pull requests: vectorch-ai/ScaleLLM

New pull request New

9 Open 398 Closed

Pull requests list

refactor: clean up load_state_dict for quant linear

#504 opened Oct 8, 2025 by guocuimi

Loading...

kernel: support fp8 kv cache

#381 opened Jan 21, 2025 by guocuimi

Loading...

[WIP] Llava support

#352 opened Nov 20, 2024 by guocuimi

Loading...

feat: added marlin qlinear support

#303 opened Aug 9, 2024 by guocuimi

Loading...

bugfix: fix multiple definition issue.

#261 opened Jul 3, 2024 by liutongxuan

Loading...

[wip] feat: add embeddings support

#246 opened Jun 20, 2024 by guocuimi

Loading...

[kernel] added half2 specialization for layernorm kernel

#139 opened Apr 22, 2024 by dongxianzhe

Loading...

7

[model] add support for mixtral moe model

#128 opened Apr 16, 2024 by 936187425

Loading...

1

benchmark test script

#124 opened Apr 13, 2024 by ShijiaTang

Loading...

2

ProTip! Exclude everything labeled bug with -label:bug.