Zhanda ZhuandYubo Gao 5d5c776444 [Perf] FP8 FlashInfer Attn for ViT (#38065) ...

Signed-off-by: Zhanda Zhu <zhandazhu@gmail.com>
Co-authored-by: Yubo Gao <ybgao-nvidia@users.noreply.github.com>

2026-04-27 13:44:15 +08:00

..

reload

[Quantization] - Layerwise reloading of Attention/KV quantized models (#38995)

2026-04-15 18:03:32 -07:00

__init__.py

[Feature] Add InstantTensor weight loader (#36139)

2026-03-14 18:05:23 +01:00

base_loader.py

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

bitsandbytes_loader.py

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

2026-03-04 09:49:47 +00:00

default_loader.py

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

dummy_loader.py

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

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

ep_weight_filter.py

[Bugfix] Fix EP weight filter breaking EPLB and NVFP4 accuracy (#37322)

2026-03-18 18:30:29 +08:00

gguf_loader.py

Update to transformers v5 (#30566)

2026-04-15 16:29:15 -07:00

runai_streamer_loader.py

[Mypy] Fix mypy for vllm/model_executor (except vllm/model_executor/layers) (#37904)

2026-03-24 17:14:01 +00:00

sharded_state_loader.py

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

tensorizer_loader.py

[Mypy] Fix mypy for vllm/model_executor (except vllm/model_executor/layers) (#37904)

2026-03-24 17:14:01 +00:00

tensorizer.py

[Mypy] Fix mypy for vllm/model_executor (except vllm/model_executor/layers) (#37904)

2026-03-24 17:14:01 +00:00

utils.py

[Perf] FP8 FlashInfer Attn for ViT (#38065)

2026-04-27 13:44:15 +08:00

weight_utils.py

[Model] Support Hy3 preview (#40681)

2026-04-23 22:08:26 +08:00