PyPI recent updates for turboquant-mlx-full https://pypi.org/project/turboquant-mlx-full/ Recent updates to the Python Package Index for turboquant-mlx-full en 0.6.1 https://pypi.org/project/turboquant-mlx-full/0.6.1/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) manjunath.shiva@gmail.com Sat, 30 May 2026 13:29:13 GMT 0.6.0 https://pypi.org/project/turboquant-mlx-full/0.6.0/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) manjunath.shiva@gmail.com Thu, 28 May 2026 17:12:59 GMT 0.5.0 https://pypi.org/project/turboquant-mlx-full/0.5.0/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) manjunath.shiva@gmail.com Tue, 26 May 2026 17:30:16 GMT 0.4.1 https://pypi.org/project/turboquant-mlx-full/0.4.1/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) manjunath.shiva@gmail.com Mon, 25 May 2026 03:25:13 GMT 0.4.0 https://pypi.org/project/turboquant-mlx-full/0.4.0/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) manjunath.shiva@gmail.com Mon, 25 May 2026 02:53:54 GMT 0.3.0 https://pypi.org/project/turboquant-mlx-full/0.3.0/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) manjunath.shiva@gmail.com Sun, 03 May 2026 07:34:58 GMT 0.2.0 https://pypi.org/project/turboquant-mlx-full/0.2.0/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Sat, 02 May 2026 02:42:18 GMT 0.1.6 https://pypi.org/project/turboquant-mlx-full/0.1.6/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Mon, 27 Apr 2026 05:29:56 GMT 0.1.5 https://pypi.org/project/turboquant-mlx-full/0.1.5/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Sun, 26 Apr 2026 03:52:57 GMT 0.1.4 https://pypi.org/project/turboquant-mlx-full/0.1.4/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Sun, 26 Apr 2026 03:35:30 GMT 0.1.3 https://pypi.org/project/turboquant-mlx-full/0.1.3/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Thu, 23 Apr 2026 13:37:25 GMT 0.1.2 https://pypi.org/project/turboquant-mlx-full/0.1.2/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Wed, 22 Apr 2026 15:20:16 GMT 0.1.1 https://pypi.org/project/turboquant-mlx-full/0.1.1/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Thu, 09 Apr 2026 07:28:10 GMT 0.1.0 https://pypi.org/project/turboquant-mlx-full/0.1.0/ Extreme weight and KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant) Tue, 07 Apr 2026 09:58:20 GMT