Merge tag 'v0.8.5' into v0.8.5-dev

dcb5624a · zhuwenwen · 55880ca2 · ba41cc90 · dcb5624a · dcb5624a
Commit dcb5624a authored Apr 29, 2025 by zhuwenwen
20 changed files
--- a/docs/source/assets/deployment/anything-llm-upload-doc.png
+++ b/docs/source/assets/deployment/anything-llm-upload-doc.png
--- a/docs/source/assets/deployment/open_webui.png
+++ b/docs/source/assets/deployment/open_webui.png
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
--- a/docs/source/contributing/model/multimodal.md
+++ b/docs/source/contributing/model/multimodal.md
--- a/docs/source/deployment/docker.md
+++ b/docs/source/deployment/docker.md
--- a/docs/source/deployment/frameworks/anything-llm.md
+++ b/docs/source/deployment/frameworks/anything-llm.md
--- a/docs/source/deployment/frameworks/index.md
+++ b/docs/source/deployment/frameworks/index.md
--- a/docs/source/deployment/frameworks/open-webui.md
+++ b/docs/source/deployment/frameworks/open-webui.md
--- a/docs/source/deployment/integrations/production-stack.md
+++ b/docs/source/deployment/integrations/production-stack.md
--- a/docs/source/deployment/security.md
+++ b/docs/source/deployment/security.md
--- a/docs/source/design/mm_processing.md
+++ b/docs/source/design/mm_processing.md
--- a/docs/source/design/v1/metrics.md
+++ b/docs/source/design/v1/metrics.md
--- a/docs/source/design/v1/torch_compile.md
+++ b/docs/source/design/v1/torch_compile.md
--- a/docs/source/features/disagg_prefill.md
+++ b/docs/source/features/disagg_prefill.md
--- a/docs/source/features/lora.md
+++ b/docs/source/features/lora.md
--- a/docs/source/features/quantization/auto_awq.md
+++ b/docs/source/features/quantization/auto_awq.md
--- a/docs/source/features/quantization/bitblas.md
+++ b/docs/source/features/quantization/bitblas.md
--- a/docs/source/features/quantization/bnb.md
+++ b/docs/source/features/quantization/bnb.md
--- a/docs/source/features/quantization/gptqmodel.md
+++ b/docs/source/features/quantization/gptqmodel.md
--- a/docs/source/features/quantization/index.md
+++ b/docs/source/features/quantization/index.md
@@ -11,6 +11,7 @@ Quantization trades off model precision for smaller memory footprint, allowing l
 supported_hardware
 auto_awq
 bnb
+bitblas
 gguf
 gptqmodel
 int4