3 people 12a34a6bc7 [ROCm][DSV4] B-preshuffle the attention fp8 projections (#46720) ...

Signed-off-by: Mehmet Cagri Kaymak <mehmet.kaymak@amd.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>

2026-07-30 13:59:52 -05:00

..

reload

[Bugfix] Wait for the linear bias before layerwise online processing (#49805)

2026-07-25 17:56:32 +00:00

__init__.py

[Migration] Migrate GGUF quantization support to plugin (#39612)

2026-06-12 12:02:21 -07:00

base_loader.py

Deprecate old FP8 online MoE quantization class (#44514)

2026-06-23 11:53:38 -07:00

bitsandbytes_loader.py

Remove more unnecessary load_weights methods (#47058)

2026-06-30 15:22:16 +01:00

default_loader.py

[CI] Avoid unnecessary Hugging Face metadata requests (#49508)

2026-07-24 12:33:53 -07:00

dummy_loader.py

[Quantization] Consolidate dummy format logic into DummyModelLoader (#38637)

2026-03-31 22:20:45 +00:00

ep_weight_filter.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

modelexpress_loader.py

[Core] Add native ModelExpress load format (#43105)

2026-05-21 16:05:01 -04:00

mtp_validation.py

[Bugfix][SpecDecode] Scope MTP completeness checks outside bucketed updates (#49178)

2026-07-21 18:56:39 -07:00

runai_streamer_loader.py

[Bugfix][Model] Allow Run:ai memory_limit sentinel values (#47337)

2026-07-05 00:08:34 +00:00

sharded_state_loader.py

[Examples] Resettle features examples. (#40995)

2026-04-28 00:33:41 -07:00

tensorizer_loader.py

[Examples][last/6] Resettle examples. (#41084)

2026-05-07 19:42:12 -07:00

tensorizer.py

[CI] Bump mypy version 1.19.1 -> 1.20.2 (#44647)

2026-06-05 14:56:27 +00:00

utils.py

[ROCm][DSV4] B-preshuffle the attention fp8 projections (#46720)

2026-07-30 13:59:52 -05:00

weight_utils.py

[Bugfix] Respect cgroup memory limits on all platforms (#49966)

2026-07-28 14:38:20 +08:00