Andreas Karatzas 9863102ed9 [CI] Reuse loaded config for cached tokenizer (#49509) ...

Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>

2026-07-24 12:32:40 -07:00

..

__init__.py

[Bugfix] Fix RuntimeError: Already borrowed by adding thread-safe Hugging Face fast-tokenizer wrappers (#41181)

2026-05-05 14:04:01 +00:00

deepseek_v4_encoding.py

[Refactor] Remove deepseek dead code (#48780)

2026-07-17 14:57:13 +00:00

deepseek_v4.py

Bump Transformers version to 5.10.4 (#41359)

2026-07-07 05:13:28 -07:00

deepseek_v32_encoding.py

[Refactor] Remove deepseek dead code (#48780)

2026-07-17 14:57:13 +00:00

deepseek_v32.py

Bump Transformers version to 5.10.4 (#41359)

2026-07-07 05:13:28 -07:00

detokenizer_utils.py

[Bugfix] Fix logprobs token-string collision from SentencePiece space… (#48674)

2026-07-20 12:17:18 +08:00

fastokens.py

Deprecated 1st generation Qwen and QwenVL models (#45131)

2026-06-10 14:55:33 +00:00

hf.py

Bump Transformers version to 5.10.4 (#41359)

2026-07-07 05:13:28 -07:00

kimi_audio.py

Add vLLM library info to Hugging Face Hub requests (#43857)

2026-05-29 14:04:58 +00:00

mistral.py

Bump Transformers version to 5.10.4 (#41359)

2026-07-07 05:13:28 -07:00

protocol.py

[CI] Fix mypy for vllm/reasoning (#35742)

2026-03-12 12:21:33 +00:00

registry.py

[CI] Reuse loaded config for cached tokenizer (#49509)

2026-07-24 12:32:40 -07:00