[doc] add install tips (#17373)

Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
2025-05-01 01:02:41 +08:00
parent 584f5fb4c6
commit 2ac74d098e
5 changed files with 29 additions and 10 deletions
--- a/docs/source/features/quantization/quantized_kvcache.md
+++ b/docs/source/features/quantization/quantized_kvcache.md
@ -126,7 +126,7 @@ oneshot(
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
 )

-# Save quantized model
+# Save quantized model: Llama-3.1-8B-Instruct-FP8-KV
 SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-KV"
 model.save_pretrained(SAVE_DIR, save_compressed=True)
 tokenizer.save_pretrained(SAVE_DIR)