Search results

Support for Qwen3-VL and up-to-date MLLM compression documentation

Status: Open.

#1056 In intel/auto-round;

· FDH21 opened on Nov 21, 2025

[Feat][CI] Enable LLMC integration test

Status: Open.

#1054 In intel/auto-round;

· yiliu30 opened on Nov 21, 2025

· 

1.0.0

Use vllm engin for eval

Status: Open.

#1050 In intel/auto-round;

· TulipDu opened on Nov 20, 2025

ram usage on Windows is much higher than that of Linux

Status: Open.

#1048 In intel/auto-round;

· wenhuach21 opened on Nov 20, 2025

quant_lm_head=True actually didn't quant the lm head linear activation.

Status: Open.

#1044 In intel/auto-round;

· a32543254 opened on Nov 18, 2025

lm_head is not converted to QuantLinear with MXFP4/8

bugSomething isn't workingSomething isn't working

high priority

Status: Open.

#1040 In intel/auto-round;

· xin3he opened on Nov 17, 2025

· 

0.9.1

v090 only linux at all

bugSomething isn't workingSomething isn't working

Status: Open.

#1038 In intel/auto-round;

· kalle07 opened on Nov 15, 2025

Support IQ quants for GGUF format

Status: Open.

#1037 In intel/auto-round;

· mingyi456 opened on Nov 15, 2025

cerebras/MiniMax-M2-REAP-172B-A10B

Status: Open.

#1036 In intel/auto-round;

· groxaxo opened on Nov 15, 2025

zai-org/GLM-4.5-Air

Status: Open.

#1033 In intel/auto-round;

· groxaxo opened on Nov 14, 2025

optimize ram usage

Status: Open.

#1032 In intel/auto-round;

· wenhuach21 opened on Nov 14, 2025

summary environment variables in AutoRound for ease-of-use

Status: Open.

#1030 In intel/auto-round;

· xin3he opened on Nov 13, 2025

· 

0.9.1