0.6.4.post1
This patch release covers bug fixes (#10347, #10349, #10348, #10352, #10363), keep compatibility for vLLMConfig usage in out of tree models (#10356)
What's Changed
- Add default value to avoid Falcon crash (#5363) by @wchen61 in https://github.com/vllm-project/vllm/pull/10347
- [Misc] Fix import error in tensorizer tests and cleanup some code by @DarkLight1337 in https://github.com/vllm-project/vllm/pull/10349
- [Doc] Remove float32 choice from --lora-dtype by @xyang16 in https://github.com/vllm-project/vllm/pull/10348
- [Bugfix] Fix fully sharded LoRA bug by @jeejeelee in https://github.com/vllm-project/vllm/pull/10352
- [Misc] Fix some help info of arg_utils to improve readability by @ShangmingCai in https://github.com/vllm-project/vllm/pull/10362
- [core][misc] keep compatibility for old-style classes by @youkaichao in https://github.com/vllm-project/vllm/pull/10356
- [Bugfix] Ensure special tokens are properly filtered out for guided structured output with MistralTokenizer by @gcalmettes in https://github.com/vllm-project/vllm/pull/10363
- [Misc] Bump up test_fused_moe tolerance by @ElizaWszola in https://github.com/vllm-project/vllm/pull/10364
- [Misc] bump mistral common version by @simon-mo in https://github.com/vllm-project/vllm/pull/10367
Full Changelog: https://github.com/vllm-project/vllm/compare/v0.6.4...v0.6.4.post1