ci: rent gpu server with 96GB (#746)

Author: JuArce

.github/workflows/benchmark-gpu.yml

@@ -33,7 +33,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  # Vast offer search: RTX 5090, >=16 cores, >=64GB RAM, >=64GB disk, verified +
+  # Vast offer search: RTX 5090, >=16 cores, >=96GB RAM, >=64GB disk, verified +
   # rentable, Blackwell-capable driver, <= cap.
   GPU_NAME: RTX_5090
   PRICE_CAP: "1"
@@ -169,7 +169,7 @@ jobs:
           MIN_DRIVER: "580"
         run: |
           # cpu_ram filter is in GB.
-          QUERY="gpu_name=${GPU_NAME} num_gpus=1 cpu_cores_effective>=16 cpu_ram>=64 disk_space>=64 verified=true rentable=true cuda_max_good>=12.8 dph_total<=${PRICE_CAP}"
+          QUERY="gpu_name=${GPU_NAME} num_gpus=1 cpu_cores_effective>=16 cpu_ram>=96 disk_space>=64 verified=true rentable=true cuda_max_good>=12.8 dph_total<=${PRICE_CAP}"
           echo "Query: $QUERY (+ client-side driver_version major >= $MIN_DRIVER)"
           # Keep only offers whose driver major >= MIN_DRIVER, then most expensive first
           # (within the price cap) — premium hosts have faster disks/network (quicker image
@@ -190,7 +190,7 @@ jobs:
             sleep "$OFFER_INTERVAL"
           done
           if [ -z "$OFFER_ID" ]; then
-            echo "::error::No RTX 5090 offer matched after $OFFER_ATTEMPTS attempts (>=16 cores, >=64GB RAM, >=64GB disk, driver>=${MIN_DRIVER}, <= \$${PRICE_CAP}/hr)"
+            echo "::error::No RTX 5090 offer matched after $OFFER_ATTEMPTS attempts (>=16 cores, >=96GB RAM, >=64GB disk, driver>=${MIN_DRIVER}, <= \$${PRICE_CAP}/hr)"
             exit 1
           fi
           echo "id=$OFFER_ID" >> "$GITHUB_OUTPUT"