AlfredXu2 commited on
Commit
702ef2b
·
1 Parent(s): b1b0320

feat: Faster prefill

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. dequant_mxfp4.xclbin +2 -2
  3. dequant_q4_1.xclbin +2 -2
  4. mm.xclbin +2 -2
.gitattributes CHANGED
@@ -41,3 +41,4 @@ attn.xclbin filter=lfs diff=lfs merge=lfs -text
41
  dequant_mxfp4.xclbin filter=lfs diff=lfs merge=lfs -text
42
  expert.xclbin filter=lfs diff=lfs merge=lfs -text
43
  mm.xclbin filter=lfs diff=lfs merge=lfs -text
 
 
41
  dequant_mxfp4.xclbin filter=lfs diff=lfs merge=lfs -text
42
  expert.xclbin filter=lfs diff=lfs merge=lfs -text
43
  mm.xclbin filter=lfs diff=lfs merge=lfs -text
44
+ *.q4nx filter=lfs diff=lfs merge=lfs -text
dequant_mxfp4.xclbin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b52787eaf72fa34f5d540ee40c706ccc9a6c3f43a47190dea66cd5beadb84d8c
3
- size 280555
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7043d18b9aaefa0accea84c0fa730545cb4c944145b92f60100517f3be61247
3
+ size 279435
dequant_q4_1.xclbin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18e24350c519521976c4a1fdb4f342a437ba9a4abedb716dca99adc5bb6e9a2a
3
- size 114667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bff000d64382748fbe4bece064b9442214b0a007ab5d5215c6e3e5453e3b31b
3
+ size 114411
mm.xclbin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d001fcc3e8b5aa553f740abedc859ded13173747c6eeb670763959322c8a936
3
- size 451611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a9f2b47a09f2e129ee057f7b4b0e95955e7bfa1e48a99172bbd3992adc369a
3
+ size 543675