https://pypi.org/project/turboquant-vllm/ Recent updates to the Python Package Index for turboquant-vllm en https://pypi.org/project/turboquant-vllm/1.5.0/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Wed, 08 Apr 2026 04:42:32 GMT https://pypi.org/project/turboquant-vllm/1.4.1/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Sat, 04 Apr 2026 00:16:28 GMT https://pypi.org/project/turboquant-vllm/1.4.0/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Wed, 01 Apr 2026 19:42:19 GMT https://pypi.org/project/turboquant-vllm/1.3.0/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Tue, 31 Mar 2026 23:54:25 GMT https://pypi.org/project/turboquant-vllm/1.2.2/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Mon, 30 Mar 2026 04:50:54 GMT https://pypi.org/project/turboquant-vllm/1.2.1/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Mon, 30 Mar 2026 01:18:54 GMT https://pypi.org/project/turboquant-vllm/1.2.0/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Sun, 29 Mar 2026 22:34:19 GMT https://pypi.org/project/turboquant-vllm/1.1.1/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Sat, 28 Mar 2026 14:31:52 GMT https://pypi.org/project/turboquant-vllm/1.1.0/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Fri, 27 Mar 2026 23:56:08 GMT https://pypi.org/project/turboquant-vllm/1.0.0/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Fri, 27 Mar 2026 22:25:35 GMT https://pypi.org/project/turboquant-vllm/0.1.0/ TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090 Fri, 27 Mar 2026 19:05:52 GMT