Commits

History for

Commits on Jun 11, 2026

Add optimized Gemma4 config (#259)
iamyashshukla
authored
b3e77ac

Commits on May 14, 2026

Update max model length and add kv-cache dtype
lk-chen
authored
d7bf4bd
Update vllm-tpu image version to 2026/05/14
lk-chen
authored
f0385bd

Commits on May 1, 2026

[Gemma4] Pin vllm-tpu image tag to nightly-20260428
lk-chen
authored
6892fe3

Commits on Apr 28, 2026

moe flag
lk-chen
authored
c2a91c7
qwix quantization
lk-chen
authored
d53af1f
Update Ironwood recipe for Gemma4
lk-chen
authored
6456e96

Commits on Apr 2, 2026

Add user-facing TODO comments to gemma4-server.yaml
RobMulla
committed
6fdf599
Address PR reviews: link external YAML, reduce storage size, and add benchmarking
RobMulla
committed
4142d2a
Rename example.yaml to gemma4-server.yaml
RobMulla
authored
74f9dc7
Remove Min TPUs column from verified models table
RobMulla
committed
79a23df
Update docs to use safe Golden Gate Bridge image in examples
RobMulla
committed
160547d
docs: Fix Gemma 4 model and image references
RobMulla
committed
4061eca

Loading