Rename Matrix6P to J6P
Browse files
README.md
CHANGED
|
@@ -29,6 +29,6 @@ Parameter counts are calculated from the tensors stored in the upstream checkpoi
|
|
| 29 |
|
| 30 |
| Chips | Data Type | ViT Image Size | Sequence Length (tokens) | Maximum Context Length (tokens) | BPU Cores (ViT / Prefill / Decode) | ViT Latency (ms) | TTFT (ms) | Prefill TPS (token/s) | Decode TPS (token/s) | BPU Memory (GB) | CPU Memory (GB) |
|
| 31 |
|---|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
|
| 32 |
-
|
|
| 33 |
|
| 34 |
> **Note:** TTFT includes preprocessing and ViT latency. Memory values represent the peak memory usage measured during the specified performance test.
|
|
|
|
| 29 |
|
| 30 |
| Chips | Data Type | ViT Image Size | Sequence Length (tokens) | Maximum Context Length (tokens) | BPU Cores (ViT / Prefill / Decode) | ViT Latency (ms) | TTFT (ms) | Prefill TPS (token/s) | Decode TPS (token/s) | BPU Memory (GB) | CPU Memory (GB) |
|
| 31 |
|---|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
|
| 32 |
+
| J6P | W8A8 | 448 × 448 | 512 | 1024 | 4 / 4 / 4 | 41.451 | 65.766 | 24,955.227 | 159.481 | 1.01 | 0.68 |
|
| 33 |
|
| 34 |
> **Note:** TTFT includes preprocessing and ViT latency. Memory values represent the peak memory usage measured during the specified performance test.
|