v1.6.0

Merge pull request #125 from runpod-workers/up-0.6.3

update vllm

v1.5.0

• vllm version update 0.6.1 --> 0.6.2.
• Supports llama 3.2 Models.

v1.4.0: Merge pull request #109 from runpod-workers/0.5.5-update

vllm version update 0.5.5 --> 0.6.1

v1.3.1

vLLm version: 0.5.5

• OpenAI Completion Requests Bug fix.

v1.3.0

Version upgrade from vllm v0.5.4 -> v0.5.5

Various improvements and bug fixes.
[Known Issue]: OpenAI Completion Requests error.

v1.2.0

Version upgrade from vllm v0.5.3 -> v0.5.4

• Various improvements and bug fixes.
• [Known Issue]: OpenAI Completion Requests error.

v1.1.0

• Major update from vllm v0.4.2 -> v0.5.3.
• supports Llama 3.1 version models.
• Various improvements and bug fixes.
  [Known Issue]: OpenAI Completion Requests error.

1.0.1

Hotfix adding backwards compatibility for deprecated max_context_len_to_capture engine argument

1.0.0

Worker vLLM 1.0.0 - What's Changed

• vLLM version 0.3.3 -> 0.4.2
• Various improvements and bug fixes

0.3.2

Worker vLLM 0.3.2 - What's Changed

• vLLM version 0.3.2 -> 0.3.3
  • StarCoder2 support
  • Performance optimization for Gemma
  • 2/3/8-bit GPTQ support
  • Integrate Marlin Kernels for Int4 GPTQ inference
  • Performance optimization for MoE kernel
• Updated and refactored base image, sampling parameters, etc.
• Various bug fixes