7mileandBenjamin Chislett b2ea5ba677 [Bugfix][Spec Decode] Fix wrong valid_mask for padded speculation when chunked prefill occurs (#26231) ...

Signed-off-by: seven-mile <i@7li.moe>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

2025-10-06 18:24:22 +00:00

..

attention

[Attention] Remove unused reorder_batch method (#24463)

2025-10-06 13:13:39 -04:00

core

[V1] [Hybrid] Some additional clean-up in Mamba2 prefix caching (#26222)

2025-10-06 10:40:30 +08:00

engine

[Frontend] Consolidate tokenizer init code (#26276)

2025-10-06 09:34:52 +00:00

executor

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

kv_offload

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

metrics

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

pool

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

sample

Fix per file ruff ignores related to simplification (#26259)

2025-10-05 20:31:53 +00:00

spec_decode

[Bugfix][Spec Decode] Fix wrong valid_mask for padded speculation when chunked prefill occurs (#26231)

2025-10-06 18:24:22 +00:00

structured_output

Fix per file ruff ignores related to typing (#26254)

2025-10-05 16:37:55 +00:00

worker

Support llama3 eagle3 head with llama4 verifier (#25961)

2025-10-06 13:56:08 -04:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

cudagraph_dispatcher.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

kv_cache_interface.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

outputs.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

request.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

serial_utils.py

Remove all references to yapf as it's no longer used (#26251)

2025-10-05 09:18:11 -07:00

utils.py

Fix per file ruff ignores related to line length (#26262)

2025-10-06 05:12:40 +00:00