update [markdown] - [cleaned] ✅

#8
Files changed (1) hide show
  1. README.md +10 -9
README.md CHANGED
@@ -41,7 +41,8 @@ This repository provides pre-built wheels for `flash-attn` version **2.8.3** for
41
 
42
  ## Linux x86_64
43
 
44
- ### Torch 2.9
 
45
  **ABI: `TRUE` (Implied)**
46
 
47
  #### Python 3.12 (`cp312`)
@@ -53,7 +54,7 @@ flash-attn @ https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse
53
 
54
  ---
55
 
56
- ### Torch 2.8
57
 
58
  #### ABI: `FALSE`
59
 
@@ -111,7 +112,7 @@ flash-attn @ https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse
111
 
112
  ---
113
 
114
- ### Torch 2.7
115
 
116
  #### ABI: `FALSE`
117
 
@@ -169,7 +170,7 @@ flash-attn @ https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse
169
 
170
  ---
171
 
172
- ### Torch 2.6
173
 
174
  #### ABI: `FALSE`
175
 
@@ -227,7 +228,7 @@ flash-attn @ https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse
227
 
228
  ---
229
 
230
- ### Torch 2.5
231
 
232
  #### ABI: `FALSE`
233
 
@@ -285,7 +286,7 @@ flash-attn @ https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse
285
 
286
  ---
287
 
288
- ### Torch 2.4
289
 
290
  #### ABI: `FALSE`
291
 
@@ -335,7 +336,7 @@ flash-attn @ https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse
335
 
336
  ## Linux aarch64 (ARM)
337
 
338
- ### Torch 2.9 (Nightly/Pre-release)
339
 
340
  #### ABI: `TRUE`
341
 
@@ -348,5 +349,5 @@ flash-attn @ https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse
348
 
349
  ## Acknowledgements and Note:
350
 
351
- - Dao-AILab [flash-attention]: [Faster Attention with Better Parallelism and Work Partitioning](https://github.com/Dao-AILab/flash-attention).
352
- - Note: This repository follows the same license, release notices, and other terms and conditions as the Dao-AILab [flash-attention](https://github.com/Dao-AILab/flash-attention) repository.
 
41
 
42
  ## Linux x86_64
43
 
44
+ ### **<span style="color:orangered;">Torch 2.9</span>**
45
+
46
  **ABI: `TRUE` (Implied)**
47
 
48
  #### Python 3.12 (`cp312`)
 
54
 
55
  ---
56
 
57
+ ### **<span style="color:orangered;">Torch 2.8</span>**
58
 
59
  #### ABI: `FALSE`
60
 
 
112
 
113
  ---
114
 
115
+ ### **<span style="color:orangered;">Torch 2.7</span>**
116
 
117
  #### ABI: `FALSE`
118
 
 
170
 
171
  ---
172
 
173
+ ### **<span style="color:orangered;">Torch 2.6</span>**
174
 
175
  #### ABI: `FALSE`
176
 
 
228
 
229
  ---
230
 
231
+ ### **<span style="color:orangered;">Torch 2.5</span>**
232
 
233
  #### ABI: `FALSE`
234
 
 
286
 
287
  ---
288
 
289
+ ### **<span style="color:orangered;">Torch 2.4</span>**
290
 
291
  #### ABI: `FALSE`
292
 
 
336
 
337
  ## Linux aarch64 (ARM)
338
 
339
+ ### **<span style="color:orangered;">Torch 2.9 (Nightly/Pre-release)</span>**
340
 
341
  #### ABI: `TRUE`
342
 
 
349
 
350
  ## Acknowledgements and Note:
351
 
352
+ - Dao-AILab [flash-attention]: [Faster Attention with Better Parallelism and Work Partitioning](https://arxiv.org/pdf/2205.14135).
353
+ - Note: This repository follows the same license, release notices, and other terms and conditions as the Dao-AILab [flash-attention](https://github.com/Dao-AILab/flash-attention) repository.