Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
---
|
| 13 |
# Qwen3.8-Flash-Next, INT4/INT6 mixed (AutoRound), for vLLM on 3x to 4x RTX 3090
|
| 14 |
|
| 15 |
-
[Article](https://minamism.com/posts/flash-next-vllm/)
|
| 16 |
|
| 17 |
This repository has a mixed-precision AutoRound 4.21bpw quantization of Qwen3.8-Flash-Next, and the vLLM patch that runs it on three 24 GB cards with 262,144 tokens of context x 4 requests with text and images.
|
| 18 |
|
|
|
|
| 12 |
---
|
| 13 |
# Qwen3.8-Flash-Next, INT4/INT6 mixed (AutoRound), for vLLM on 3x to 4x RTX 3090
|
| 14 |
|
| 15 |
+
[Article](https://minamism.com/posts/flash-next-vllm/), [Article #2](https://minamism.com/posts/flash-next-vllm-optimization/)
|
| 16 |
|
| 17 |
This repository has a mixed-precision AutoRound 4.21bpw quantization of Qwen3.8-Flash-Next, and the vLLM patch that runs it on three 24 GB cards with 262,144 tokens of context x 4 requests with text and images.
|
| 18 |
|