Support compute_dtype for FP4/FP8 tensor core FLOPS selection

Add `compute_dtype` field to ModelConfig ("bf16", "fp8", "fp4") which
controls two things:
- GPU FLOPS tier: auto-selects from preset FP4/FP8/BF16 TFLOPS
- Weight bytes: uses 0.5/1.0/2.0 bytes per param for memory-bound check

Hardware presets now include per-GPU FP8 and FP4 dense FLOPS for all
GPUs that support them (H100/H800/H20: FP8, B200/B300: FP8+FP4).
Config resolution auto-selects the right FLOPS when compute_dtype is
set and the user hasn't explicitly overridden gpu_flops.

GLM-5-NVFP4 on 8xB300 now correctly uses 13.5 PFLOPS/GPU FP4 (6x
faster prefill) and 0.5 bytes/param weights (halved memory footprint).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

configs/glm5-nvfp4-8xb300.yaml

@@ -7,7 +7,8 @@
 model:
   config_json: ../models/GLM-5-NVFP4/config.json
   name: glm-5-nvfp4
-  dtype_bytes: 1               # FP8 KV cache
+  compute_dtype: fp4            # FP4 weights → selects FP4 tensor core FLOPS
+  dtype_bytes: 1                # FP8 KV cache
   block_size_tokens: 512
 
 hardware: