-
model card
-
truss deployment example
-
model card
-
model card: simplify truss push examples
-
processor docstring
-
sglang plugin
-
remove vLLM plugin
-
remove vLLM plugin
-
remove vLLM plugin
-
remove vLLM plugin
-
model card: trim intro
-
model card: sglang only
-
model card: remove build/known-issues sections
-
model card: table header
-
model card: fp8-only, with 8- and 4-GPU examples
-
truss deployment example
-
model card: 4-GPU NVFP4 option
-
config belongs to the other variant
-
truss deployment example
-
model card: 1M context, no source-repo links, truss ships in-repo
-
remove AppleDouble files
-
remove AppleDouble files
-
configuration_glm5v: drop layer_types before AutoConfig + vt_* aliasing (proven NVFP4 SGLang recipe)
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
remove stale/AppleDouble files
-
Add files using upload-large-folder tool
-
Add files using upload-large-folder tool
-
Add files using upload-large-folder tool
-
engine plugin (vllm + sglang)
-
model card
-
initial commit