prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant

tests/test_config.py

@@ -107,6 +107,23 @@ mode = "auto"
         self.assertEqual(config.stats_path, os.path.expanduser("~/s.json"))
         self.assertEqual(config.trace_path, "/abs/t.gz")
 
+    def test_miss_min_weight(self):
+        config = mc.load_config(self.write("m.toml", 'pack_dir = "/p"\n[miss]\nmin_weight = 0.7\n'))
+        self.assertEqual(config.miss.min_weight, 0.7)
+        self.assertEqual(mc.Miss().min_weight, 1.0)  # default: compute every routed expert
+        with self.assertRaisesRegex(ValueError, "min_weight must be a number in"):
+            mc.load_config(self.write("m2.toml", 'pack_dir = "/p"\n[miss]\nmin_weight = 1.5\n'))
+
+    def test_quant_key_and_expert_sizes(self):
+        self.assertEqual(mc.load_config(self.write("q.toml", 'pack_dir = "/p"\nquant = "int4"\n')).quant, "int4")
+        self.assertEqual(mc.load_config(self.write("b.toml", 'pack_dir = "/p"\n')).quant, "bf16")
+        with self.assertRaisesRegex(ValueError, "quant must be one of"):
+            mc.load_config(self.write("bad.toml", 'pack_dir = "/p"\nquant = "int3"\n'))
+        h, i = 2816, 704
+        self.assertEqual(mc.expert_bytes(h, i), 3 * h * i * 2)
+        self.assertEqual(mc.expert_bytes(h, i, "int8"), 3 * h * i + 4 * (2 * i + h))  # fp32 row scales
+        self.assertEqual(mc.expert_bytes(h, i, "int4"), 3 * h * i // 2 + 2 * 3 * h * i // 64)
+
     def test_serve_and_draft_tables(self):
         config = mc.load_config(self.write("s.toml", 'pack_dir = "/p"\n[serve]\nmax_requests = 4\n'
                                                      'kv_cache_gib = 1.5\n[draft]\nfull_requests = 2\n'