Add files using upload-large-folder tool

.gitattributes

@@ -39,3 +39,5 @@ Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv4096.task filter=lfs diff=lfs merg
 Qwen2.5-1.5B-Instruct_seq128_q8_ekv4096.task filter=lfs diff=lfs merge=lfs -text
 Qwen2.5-1.5B-Instruct_seq128_q8_ekv1280.task filter=lfs diff=lfs merge=lfs -text
 Qwen2.5-1.5B-Instruct_multi-prefill-seq_f32_ekv4096.task filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv4096.litertlm filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-Instruct_multi-prefill-seq_f32_ekv4096.litertlm filter=lfs diff=lfs merge=lfs -text

Qwen2.5-1.5B-Instruct_multi-prefill-seq_f32_ekv4096.litertlm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708483abb477c10dd8db8cc6b4995bbd9cd2deda5539249a37c218028a669391
+size 6182436864

Qwen2.5-1.5B-Instruct_multi-prefill-seq_f32_ekv4096.task

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6bf44f952218b22a76cc1b94ac46a5db8dc43c7f31b7e635f2ca608e3f35ed
-size 4296491008
+oid sha256:addf45e6d75f60c9cd34bdf42d84f896f5b7b4faba6ee9f631bf6139de6af087
+size 6182391796

Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv4096.litertlm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac49902133f729199bbd23ad6714df32b20585c786f2546d2293cc371f35278
+size 1598603264

Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv4096.task

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a662d1af6ca2c750bc047738d6f48441d4b6968062c24ef52fcff5d693291f6
-size 1597913616
+oid sha256:82968d0a6c3872cf016fdbcfc591571605f4c7fd2b0f64d2533df502cc6596b3
+size 1598556720

README.md

@@ -62,8 +62,8 @@ Note that all benchmark stats are from a Samsung S24 Ultra and multiple prefill
    <th></th>
   </tr>
   <tr>
-<td rowspan="3"><p style="text-align: left">CPU</p></td>
-<td><p style="text-align: left">fp32 (baseline)</p></td>
+<td rowspan="5"><p style="text-align: left">CPU</p></td>
+<td rowspan="3"><p style="text-align: left">fp32 (baseline)</p></td>
 <td><p style="text-align: right">1280</p></td>
 <td><p style="text-align: right">27 tk/s</p></td>
 <td><p style="text-align: right">6 tk/s</p></td>
@@ -74,8 +74,7 @@ Note that all benchmark stats are from a Samsung S24 Ultra and multiple prefill
 <td><p style="text-align: left"><a style="text-decoration: none" href="https://huggingface.co/litert-community/Qwen2.5-1.5B-Instruct/resolve/main/Qwen2.5-1.5B-Instruct_multi-prefill-seq_f32_ekv1280.task">&#128279;</a></p></td>
 </tr>
 <tr>
-<td rowspan="4"><p style="text-align: left">dynamic_int8</p></td>
-<td><p style="text-align: right">1280</p></td>
+<td rowspan="2"><p style="text-align: right">1280</p></td>
 <td><p style="text-align: right">106 tk/s</p></td>
 <td><p style="text-align: right">23 tk/s</p></td>
 <td><p style="text-align: right">2.74 s</p></td>
@@ -85,7 +84,6 @@ Note that all benchmark stats are from a Samsung S24 Ultra and multiple prefill
 <td><p style="text-align: left"><a style="text-decoration: none" href="https://huggingface.co/litert-community/Qwen2.5-1.5B-Instruct/resolve/main/Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv1280.task">&#128279;</a></p></td>
 </tr>
 <tr>
-<td><p style="text-align: right">4096</p></td>
 <td><p style="text-align: right">63 tk/s</p></td>
 <td><p style="text-align: right">20 tk/s</p></td>
 <td><p style="text-align: right">4.40 s</p></td>
@@ -95,8 +93,8 @@ Note that all benchmark stats are from a Samsung S24 Ultra and multiple prefill
 <td><p style="text-align: left"><a style="text-decoration: none" href="https://huggingface.co/litert-community/Qwen2.5-1.5B-Instruct/resolve/main/Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv4096.task">&#128279;</a></p></td>
 </tr>
 <tr>
-<td rowspan="2"><p style="text-align: left">GPU</p></td>
-<td><p style="text-align: right">1280</p></td>
+<td rowspan="2"><p style="text-align: left">dynamic_int8</p></td>
+<td rowspan="2"><p style="text-align: right">1280</p></td>
 <td><p style="text-align: right">706 tk/s</p></td>
 <td><p style="text-align: right">24 tk/s</p></td>
 <td><p style="text-align: right">6.94 s</p></td>
@@ -106,7 +104,6 @@ Note that all benchmark stats are from a Samsung S24 Ultra and multiple prefill
 <td><p style="text-align: left"><a style="text-decoration: none" href="https://huggingface.co/litert-community/Qwen2.5-1.5B-Instruct/resolve/main/Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv1280.task">&#128279;</a></p></td>
 </tr>
 <tr>
-<td><p style="text-align: right">4096</p></td>
 <td><p style="text-align: right">417 tk/s</p></td>
 <td><p style="text-align: right">22 tk/s</p></td>
 <td><p style="text-align: right">7.93 s</p></td>