intel/auto-round

Pull Requests Commits

fix: correct indentation for apply_chat_template in get_ultrachat_dataset function

chensuyue committed 25 days ago

14630703

fix: update default calibration dataset from NeelNanda/pile-10k to HuggingFaceH4/ultrachat_200k

chensuyue committed 25 days ago

0aa359ac

Don't rewrite packed modules as float weights when resuming (#2386)

Shubham-Padkonde committed 26 days ago

Verified 4663212a

fix: update field extraction for ServerArgs in _run_sglang_worker (#2474)

xin3he committed 26 days ago

Verified a0651215

fix: update dependencies to include timm in unit test environment (#2473)

XuehaoSun committed 26 days ago

Verified 421ae1af

fix: skip layers the AWQ GEMM kernel cannot serve in AWQ export (#2456)

losewayy committed 28 days ago

Verified 7a660e16

fix: remove duplicate dataset aliases (#2470)

changwangss committed 28 days ago

Verified 0027ecff

bump version for auto-round-lib (#2458)

chensuyue committed 28 days ago

Verified 57230c2b

fix: enhance model evaluation preparation for non-task-based evaluation (#2468)

xin3he committed 28 days ago

Verified 1f421d6d

fix torch compile (#2459)

wenhuach21 committed 28 days ago

Verified 799ebee7

fix: keep model obj evaluation for regular workflow (#2454)

xin3he committed 28 days ago

Verified ea35ee11

fix: match layer names ending with a digit in ignore_layers (#2435)

kwy404 committed 28 days ago

Verified 5aef837e

Add requests into main requirements.txt (#2441)

chensuyue committed 29 days ago

Verified cba7a4f4

fix: forward pipeline call kwargs through diffusion entry (#2448)

changwangss committed 29 days ago

Verified 63895ebf

fix: keep make_q3_quants sums in sync with accepted levels (#2439)

raashish1601 committed 30 days ago

Verified 7059a8b1

fix: correct Q5_K GGUF packing (#2437)

raashish1601 committed 30 days ago

Verified b73d89d3

fix: keep 0 in the range of GGUF asymmetric K-quant groups (#2438)

raashish1601 committed 30 days ago

Verified 5a113d1c

fix: give attn_v of LLM_TYPE_70B models Q5_K like llama.cpp (#2443)

raashish1601 committed 30 days ago

Verified ae21ef9b

Fix CUDA UT timm issue (#2444)

XuehaoSun committed 30 days ago

Verified f5cfe304

[pre-commit.ci] pre-commit autoupdate (#2436)

pre-commit-ci[bot] committed 30 days ago

Verified 87734fb0

chore: enable ruff default rules and fix violations (#2434)

XuehaoSun committed 30 days ago

Verified c915fdcf

fix: apply debug layer limits to nested configs (#2431)

Shubham-Padkonde committed 38 days ago

Verified 6afaecdb

docs: explain Windows Triton compilation prerequisites (#2432)

Shubham-Padkonde committed 38 days ago

Verified 8cef3d9b

Bump version and upgrade python version (#2429)

XuehaoSun committed 38 days ago

Verified 1bd739fc

add mxuint (#2425)

wenhuach21 committed 38 days ago

Verified 7c4b6e92

update README.md (#2428)

wenhuach21 committed 38 days ago

Verified 4286cf93

fix: return the repaired string from escape_invalid_json_backslashes (#2419)

Shubham-Padkonde committed 38 days ago

Verified ba12c951

Keep the case of the AR_WORK_SPACE path (#2417)

Shubham-Padkonde committed 38 days ago

Verified 11949312

fix: honor AR_WORK_SPACE for the AudioCaps dataset cache (#2420)

Shubham-Padkonde committed 38 days ago

Verified 1ace02c5

INC integration test bug fix (#2423)

chensuyue committed 38 days ago

Verified 5606837a

Older