flashinfer-python 0.2.11.post1__tar.gz → 0.2.11.post2__tar.gz

{flashinfer_python-0.2.11.post1 → flashinfer_python-0.2.11.post2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flashinfer-python
-Version: 0.2.11.post1
+Version: 0.2.11.post2
 Summary: FlashInfer: Kernel Library for LLM Serving
 Author: FlashInfer team
 Project-URL: Homepage, https://github.com/flashinfer-ai/flashinfer
@@ -66,21 +66,7 @@ Using our PyTorch API is the easiest way to get started:
 
 ### Install from PIP
 
-We provide prebuilt python wheels for Linux. Install FlashInfer with the following command:
-
-```bash
-# For CUDA 12.6 & torch 2.6
-pip install flashinfer-python -i https://flashinfer.ai/whl/cu126/torch2.6
-# For other CUDA & torch versions, check https://docs.flashinfer.ai/installation.html
-```
-
-To try the latest features from the main branch, use our nightly-built wheels:
-
-```bash
-pip install flashinfer-python -i https://flashinfer.ai/whl/nightly/cu126/torch2.6
-```
-
-For a JIT version (compiling every kernel from scratch, [NVCC](https://developer.nvidia.com/cuda-downloads) is required), install from [PyPI](https://pypi.org/project/flashinfer-python/):
+FlashInfer is available as a Python package for Linux on PyPI. You can install it with the following command:
 
 ```bash
 pip install flashinfer-python

{flashinfer_python-0.2.11.post1 → flashinfer_python-0.2.11.post2}/README.md

@@ -45,21 +45,7 @@ Using our PyTorch API is the easiest way to get started:
 
 ### Install from PIP
 
-We provide prebuilt python wheels for Linux. Install FlashInfer with the following command:
-
-```bash
-# For CUDA 12.6 & torch 2.6
-pip install flashinfer-python -i https://flashinfer.ai/whl/cu126/torch2.6
-# For other CUDA & torch versions, check https://docs.flashinfer.ai/installation.html
-```
-
-To try the latest features from the main branch, use our nightly-built wheels:
-
-```bash
-pip install flashinfer-python -i https://flashinfer.ai/whl/nightly/cu126/torch2.6
-```
-
-For a JIT version (compiling every kernel from scratch, [NVCC](https://developer.nvidia.com/cuda-downloads) is required), install from [PyPI](https://pypi.org/project/flashinfer-python/):
+FlashInfer is available as a Python package for Linux on PyPI. You can install it with the following command:
 
 ```bash
 pip install flashinfer-python

{flashinfer_python-0.2.11.post1 → flashinfer_python-0.2.11.post2}/csrc/fp8_gemm_cutlass.jinja

@@ -20,6 +20,7 @@ namespace flashinfer {
 namespace gemm {
     INSTANCE_FP8_GEMM_TEMPLATE_SM100({{ type }}, {{ cta_m }}, {{ cta_n }}, {{ cta_k }}, 1, 1, 1, _1SM);
     INSTANCE_FP8_GEMM_TEMPLATE_SM100({{ type }}, {{ cta_m }}, {{ cta_n }}, {{ cta_k }}, 1, 2, 1, _1SM);
+    INSTANCE_FP8_GEMM_TEMPLATE_SM100({{ type }}, {{ cta_m }}, {{ cta_n }}, {{ cta_k }}, 1, 4, 1, _1SM);
     INSTANCE_FP8_GEMM_TEMPLATE_SM100({{ type }}, {{ cta_m }}, {{ cta_n }}, {{ cta_k }}, 2, 1, 1, _2SM);
     INSTANCE_FP8_GEMM_TEMPLATE_SM100({{ type }}, {{ cta_m }}, {{ cta_n }}, {{ cta_k }}, 2, 2, 1, _2SM);
 }  // namespace gemm