Add support for GPTQ-quantized MoE models using MoE Marlin

This change add support for MoE models that use GPTQ quantization.
Currently only models with the following properties are supported:

- No `desc_act` with tensor parallelism, unless `group_size=-1`.
- No asymmetric quantization.
- No AWQ.

flake.nix

@@ -5,7 +5,7 @@
       inputs.nixpkgs.follows = "tgi-nix/nixpkgs";
     };
     nix-filter.url = "github:numtide/nix-filter";
-    tgi-nix.url = "github:huggingface/text-generation-inference-nix";
+    tgi-nix.url = "github:danieldk/tgi-nix/moe-kernels-0.4.0";
     nixpkgs.follows = "tgi-nix/nixpkgs";
     flake-utils.url = "github:numtide/flake-utils";
     rust-overlay = {

integration-tests/models/__snapshots__/test_flash_mixtral_gptq/test_flash_mixtral_gptq.json

@@ -0,0 +1,89 @@
+{
+  "details": {
+    "best_of_sequences": null,
+    "finish_reason": "length",
+    "generated_tokens": 10,
+    "prefill": [
+      {
+        "id": 1,
+        "logprob": null,
+        "text": "<s>"
+      },
+      {
+        "id": 3735,
+        "logprob": -11.0078125,
+        "text": "Test"
+      },
+      {
+        "id": 2159,
+        "logprob": -13.59375,
+        "text": "request"
+      }
+    ],
+    "seed": null,
+    "tokens": [
+      {
+        "id": 13,
+        "logprob": -1.7089844,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 13,
+        "logprob": -0.68847656,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 28771,
+        "logprob": -1.9394531,
+        "special": false,
+        "text": "#"
+      },
+      {
+        "id": 3735,
+        "logprob": -2.8808594,
+        "special": false,
+        "text": " Test"
+      },
+      {
+        "id": 2159,
+        "logprob": -0.37280273,
+        "special": false,
+        "text": " request"
+      },
+      {
+        "id": 13,
+        "logprob": -0.26098633,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 13,
+        "logprob": -0.0017137527,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 1064,
+        "logprob": -2.2695312,
+        "special": false,
+        "text": "##"
+      },
+      {
+        "id": 3735,
+        "logprob": -1.9238281,
+        "special": false,
+        "text": " Test"
+      },
+      {
+        "id": 2159,
+        "logprob": -0.48828125,
+        "special": false,
+        "text": " request"
+      }
+    ],
+    "top_tokens": null
+  },
+  "generated_text": "\n\n# Test request\n\n## Test request"
+}

integration-tests/models/__snapshots__/test_flash_mixtral_gptq/test_flash_mixtral_gptq_all_params.json

@@ -0,0 +1,89 @@
+{
+  "details": {
+    "best_of_sequences": null,
+    "finish_reason": "length",
+    "generated_tokens": 10,
+    "prefill": [
+      {
+        "id": 1,
+        "logprob": null,
+        "text": "<s>"
+      },
+      {
+        "id": 3735,
+        "logprob": -11.0078125,
+        "text": "Test"
+      },
+      {
+        "id": 2159,
+        "logprob": -13.59375,
+        "text": "request"
+      }
+    ],
+    "seed": 0,
+    "tokens": [
+      {
+        "id": 13,
+        "logprob": -0.34838867,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 13940,
+        "logprob": -0.38916016,
+        "special": false,
+        "text": "``"
+      },
+      {
+        "id": 28832,
+        "logprob": 0.0,
+        "special": false,
+        "text": "`"
+      },
+      {
+        "id": 3371,
+        "logprob": -1.2529297,
+        "special": false,
+        "text": "json"
+      },
+      {
+        "id": 13,
+        "logprob": 0.0,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 28751,
+        "logprob": 0.0,
+        "special": false,
+        "text": "{"
+      },
+      {
+        "id": 13,
+        "logprob": 0.0,
+        "special": false,
+        "text": "\n"
+      },
+      {
+        "id": 2287,
+        "logprob": 0.0,
+        "special": false,
+        "text": "   "
+      },
+      {
+        "id": 345,
+        "logprob": 0.0,
+        "special": false,
+        "text": " \""
+      },
+      {
+        "id": 3134,
+        "logprob": -0.640625,
+        "special": false,
+        "text": "request"
+      }
+    ],
+    "top_tokens": null
+  },
+  "generated_text": "Test request\n```json\n{\n    \"request"
+}