Skip to content

Commit 3678702

Browse files
committed
Fix duplicate title
1 parent 5991232 commit 3678702

File tree

1 file changed

+1
-3
lines changed

1 file changed

+1
-3
lines changed

_posts/2025-02-24-ptpc-fp8-rocm.md

+1-3
Original file line numberDiff line numberDiff line change
@@ -7,8 +7,6 @@ thumbnail-img: /assets/figures/ptpc/PTPC-tumbnail.png
77
share-img: /assets/figures/ptpc/PTPC-tumbnail.png
88
---
99

10-
# **Boosting vLLM Performance on AMD ROCm: PTPC-FP8 Quantization Unleashes Speed and Accuracy**
11-
1210
**TL;DR**: vLLM on AMD ROCm now has better FP8 performance!
1311

1412
* **What's new?** [PTPC-FP8 quantization](https://github.com/vllm-project/vllm/pull/12501) is now supported in vLLM (v0.7.3+) on AMD ROCm.
@@ -297,4 +295,4 @@ lm_eval \
297295
--model vllm \
298296
--model_args pretrained=$MODEL,add_bos_token=True,kv_cache_dtype=auto \
299297
--tasks gsm8k --num_fewshot 5 --batch_size auto --limit 250
300-
```
298+
```

0 commit comments

Comments
 (0)