Compare commits

..
4 Commits
Author SHA1 Message Date
Doug Smithandkhluu 4286e16274 [Release] Include source distribution (sdist) in PyPI uploads (#35136)
Signed-off-by: dougbtv <dosmith@redhat.com>
Co-authored-by: Daniele Trifirò <dtrifiro@redhat.com>
(cherry picked from commit 0bfa229bf1)
2026-03-05 18:24:31 -08:00
Avery Miaoandkhluu cd837b2d76 [BUGFIX]Fix Qwen-Omni models audio max_token_per_item estimation error leading to encoder_cache_size is 0 (#35994)
Signed-off-by: Miao, Avery <avery.miao@intel.com>
(cherry picked from commit e998fa76b9)
2026-03-05 18:24:06 -08:00
Cyrus Leungandkhluu 52de5e42cd [Bugfix] Fix Qwen-VL tokenizer implementation (#36140)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
(cherry picked from commit 7196348157)
2026-03-05 18:23:32 -08:00
Kunshang Jiandkhluu 600de66bf9 [XPU] bump vllm-xpu-kernels to v0.1.3 (#35984)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
(cherry picked from commit a8f66cbde8)
2026-03-05 18:23:18 -08:00
+1 -1
View File
@@ -12,7 +12,7 @@ tokenizers >= 0.21.1 # Required for fast incremental detokenization.
protobuf >= 5.29.6, !=6.30.*, !=6.31.*, !=6.32.*, !=6.33.0.*, !=6.33.1.*, !=6.33.2.*, !=6.33.3.*, !=6.33.4.* # Required by LlamaTokenizer, gRPC. CVE-2026-0994
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
aiohttp >= 3.13.3
openai >= 1.99.1, < 2.25.0 # For Responses API with reasoning content
openai >= 1.99.1 # For Responses API with reasoning content
pydantic >= 2.12.0
prometheus_client >= 0.18.0
pillow # Required for image processing