biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Update Marlin support matrix for Turing (#34319)

Browse Source 
Signed-off-by: Tianqi Ren <tianqi.r@outlook.com>
This commit is contained in:
Tianqi Ren
2026-02-11 17:03:41 +08:00
committed by GitHub
parent 79504027ef
commit 786806dd44
2 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/features/quantization/README.md
View File

@@ -48,7 +48,7 @@ th:not(:first-child) {
|-----------------------|---------|----------|----------|-------|----------|-----------|-------------|-----------|
| AWQ | ❌ | ✅︎ | ✅︎ | ✅︎ | ✅︎ | ❌ | ✅︎ | ✅︎ |
| GPTQ | ✅︎ | ✅︎ | ✅︎ | ✅︎ | ✅︎ | ❌ | ✅︎ | ✅︎ |
| Marlin (GPTQ/AWQ/FP8) | ❌ | ❌ | ✅︎ | ✅︎ | ✅︎ | ❌ | ❌ | ❌ |
| Marlin (GPTQ/AWQ/FP8/FP4) | ❌ | ✅︎* | ✅︎ | ✅︎ | ✅︎ | ❌ | ❌ | ❌ |
| INT8 (W8A8) | ❌ | ✅︎ | ✅︎ | ✅︎ | ✅︎ | ❌ | ❌ | ✅︎ |
| FP8 (W8A8) | ❌ | ❌ | ❌ | ✅︎ | ✅︎ | ✅︎ | ❌ | ❌ |
| bitsandbytes | ✅︎ | ✅︎ | ✅︎ | ✅︎ | ✅︎ | ❌ | ❌ | ❌ |
@@ -59,6 +59,7 @@ th:not(:first-child) {
- ✅︎ indicates that the quantization method is supported on the specified hardware.
- ❌ indicates that the quantization method is not supported on the specified hardware.
- All Intel Gaudi quantization support has been migrated to [vLLM-Gaudi](https://github.com/vllm-project/vllm-gaudi).
- *Turing does not support Marlin MXFP4.
!!! note
For information on quantization support on Google TPU, please refer to the [TPU-Inference Recommended Models and Features](https://docs.vllm.ai/projects/tpu/en/latest/recommended_models_features/) documentation.