intel/auto-round

Pull Requests Commits
Refactor build process to use 'uv build' instead of 'python setup.py' (#1495)
XuehaoSun committed 13 days ago
Verified 50246114
Fix Inference tensors do not track version counter error (#1502)
mengniwang95 committed 13 days ago
Verified e2b88a5c
Enable more xpu instance for xpu CI (#1521)
chensuyue committed 13 days ago
Verified 30e4043f
fix bug of quantizing Z-image (#1516)
xin3he committed 13 days ago
Verified 8a404ec0
Fix CUDA UT and HPU UT (#1514)
XuehaoSun committed 13 days ago
Verified 89f99ae0
release CUDA memory in WeightConverter and avoid meaningless print (#1498)
xin3he committed 13 days ago
Verified cd10eab0
fix low_gpu default value, refine doc (#1520)
WeiweiZhang1 committed 13 days ago
Verified 279637de
[BUG] update moe check logic and make .gate ignore general (#1517)
xin3he committed 14 days ago
Verified 2eaa3b14
reduce ram&vram usage for vlm calib stage (#1488)
WeiweiZhang1 committed 14 days ago
Verified be387131
support minimax_m2 ignore layer: block_sparse_moe.gate (#1508)
xin3he committed 14 days ago
Verified a32224d3
Fix FP8 quantizer for Transformers v4 (#1504)
yiliu30 committed 14 days ago
Verified 6ab2db2b
Update README.md: Add nightly installation instructions for auto-round (#1505)
chensuyue committed 14 days ago
Verified 1bca8f72
[bug fix] force ignore mlp.gate (#1501)
xin3he committed 18 days ago
Verified f5f6b059
Add handle_generation_config function to manage model generation_config saving failure (#1448)
xin3he committed 18 days ago
Verified 32c1e3c1
Update MOE linear_loop implementation for speedup and matching name in vLLM (#1478)
xin3he committed 19 days ago
Verified d1501180
Update torch to 2.10.0 in CPU CI (#1492)
XuehaoSun committed 19 days ago
Verified 1e72e6a9
gguf better support for transformers5.0 and fix bug of Qwen3Next (#1474)
n1ck-guo committed 20 days ago
Verified ab14698c
Grep core dumped issue in UT test (#1484)
chensuyue committed 20 days ago
Verified c2152e48
add qwen35 ut (#1482)
wenhuach21 committed 20 days ago
Verified 2b5d1175
support qwen3_5 moe (#1476)
wenhuach21 committed 21 days ago
Verified 1b37c316
Fix typo: remove extra backtick in comment (#1481)
04cb committed 21 days ago
Verified 34acefd5
Fix HPU CI: apply temporary version restriction on compressed_tensors (#1479)
XuehaoSun committed 23 days ago
Verified 81d27d2b
Add envs.py for environment checks and update imports in test files (#1432)
xin3he committed 23 days ago
Verified 388e6c0b
reduce AutoGPTQ priority and add transformer requirement (#1467)
xin3he committed 23 days ago
Verified e7e1c78d
fix: qwen3-next NVFP4 quantization returns act_max incorrectly (#1470)
xin3he committed 23 days ago
Verified 229d1fef
Fix cuda ut workflow (#1472)
XuehaoSun committed 23 days ago
Verified b55ffb90
support glm5 (#1466)
wenhuach21 committed 25 days ago
Verified 62c9808d
Fix KeyError when GPU is missing from accelerate max_memory (#1457)
lvliang-intel committed 25 days ago
Verified b697e1d2
support multiple device evaluation for activation quantized model (#1394)
wenhuach21 committed 26 days ago
Verified bd4241df
Update compatibility test and version to 0.10.2 (#1463)
XuehaoSun committed 26 days ago
Verified 23c16c6c
Terms Of Use Privacy Policy Refund Policy Impressum