chore: import upstream snapshot with attribution

2026-07-13 12:55:37 +08:00
commit 7ce4c8e27e
5900 changed files with 1668062 additions and 0 deletions
@@ -0,0 +1,49 @@
+# GPQA Evaluation using GPT-OSS
+
+This directory contains GPQA evaluation tests using the GPT-OSS evaluation package and vLLM server.
+
+## Usage
+
+### Run tests with pytest (like buildkite)
+
+```bash
+# H200
+pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py \
+    --config-list-file=configs/models-h200.txt
+
+# B200
+pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py \
+    --config-list-file=configs/models-b200.txt
+```
+
+## Configuration Format
+
+Model configs in `configs/` directory use this YAML format:
+
+```yaml
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568          # Minimum expected accuracy
+reasoning_effort: "low"          # Reasoning effort level (default: "low")
+server_args: "--tensor-parallel-size 2"  # Server arguments
+startup_max_wait_seconds: 1800   # Max wait for server startup (default: 1800)
+env:                             # Environment variables (optional)
+  SOME_VAR: "value"
+```
+
+The `server_args` field accepts any arguments that can be passed to `vllm serve`.
+
+The `env` field accepts a dictionary of environment variables to set for the server process.
+
+## Adding New Models
+
+1. Create a new YAML config file in the `configs/` directory
+2. Add the filename to the appropriate `models-*.txt` file
+
+## Tiktoken Encoding Files
+
+The tiktoken encoding files required by the vLLM server are automatically downloaded from OpenAI's public blob storage on first run:
+
+- `cl100k_base.tiktoken`
+- `o200k_base.tiktoken`
+
+Files are cached in the `data/` directory. The `TIKTOKEN_ENCODINGS_BASE` environment variable is automatically set to point to this directory when running evaluations.
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2"
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2 --moe-backend flashinfer_cutlass"
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2 --moe-backend flashinfer_trtllm"
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2 --moe-backend flashinfer_cutlass --quantization-config.moe.activation mxfp8"
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2 --moe-backend marlin --linear-backend marlin"
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: openai/gpt-oss-20b
+metric_threshold: 0.568
+reasoning_effort: low
+server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN --tensor-parallel-size 2"
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: amd/gpt-oss-20b-w-mxfp4-a-bf16
+metric_threshold: 0.568
+reasoning_effort: low
+server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN --moe-backend aiter --tokenizer openai/gpt-oss-20b --tensor-parallel-size 2"
+env:
+  VLLM_ROCM_USE_AITER: "1"
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: amd/gpt-oss-20b-w-mxfp4-a-bf16
+metric_threshold: 0.568
+reasoning_effort: low
+server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN --moe-backend triton --tokenizer openai/gpt-oss-20b --tensor-parallel-size 2"
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8
+metric_threshold: 0.568
+reasoning_effort: low
+server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN --tensor-parallel-size 2"
+env:
+  VLLM_ROCM_USE_AITER: "1"
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2 --quantization-config.moe.activation mxfp8"
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
@@ -0,0 +1,5 @@
+# B200 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-flashinfer-mxfp4-bf16-trtllm.yaml
+gpt-oss-20b-flashinfer-mxfp4-mxfp8-cutlass.yaml
+gpt-oss-20b-sm100-fi-mxfp4-mxfp8-trtllm.yaml
@@ -0,0 +1,3 @@
+# GFX942 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-rocm-baseline.yaml
@@ -0,0 +1,6 @@
+# GFX950 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-rocm-baseline.yaml
+gpt-oss-20b-rocm-quark-mxfp4-bf16-aiter.yaml
+gpt-oss-20b-rocm-quark-mxfp4-bf16-triton.yaml
+gpt-oss-20b-rocm-quark-mxfp4-fp8-triton.yaml
@@ -0,0 +1,5 @@
+# H100 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-baseline.yaml
+gpt-oss-20b-flashinfer-mxfp4-bf16-cutlass.yaml
+gpt-oss-20b-marlin.yaml
@@ -0,0 +1,2 @@
+# DGX Spark model configurations for GPQA evaluation
+gpt-oss-20b-sm120.yaml
@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""
+Pytest configuration for GPT-OSS evaluation tests.
+"""
+
+from pathlib import Path
+
+
+def pytest_addoption(parser):
+    """Add custom command line options."""
+    parser.addoption(
+        "--config-list-file",
+        required=True,
+        help="File containing list of config files to test",
+    )
+
+
+def pytest_generate_tests(metafunc):
+    """Generate test parameters from config files."""
+    if "config_filename" in metafunc.fixturenames:
+        config_list_file = metafunc.config.getoption("--config-list-file")
+
+        # Handle both relative and absolute paths
+        config_list_path = Path(config_list_file)
+        if not config_list_path.is_absolute():
+            # If relative, try relative to test directory first
+            test_dir_path = Path(__file__).parent / config_list_file
+            if test_dir_path.exists():
+                config_list_path = test_dir_path
+            else:
+                # Try relative to current working directory
+                config_list_path = Path.cwd() / config_list_file
+
+        print(f"Looking for config list at: {config_list_path}")
+
+        config_files = []
+        if config_list_path.exists():
+            # Determine config directory (same directory as the list file)
+            config_dir = config_list_path.parent
+
+            with open(config_list_path) as f:
+                for line in f:
+                    line = line.strip()
+                    if line and not line.startswith("#"):
+                        config_path = config_dir / line
+                        print(f"Checking config file: {config_path}")
+                        if config_path.exists():
+                            config_files.append(config_path)
+                            print(f"  Found: {config_path}")
+                        else:
+                            print(f"  Missing: {config_path}")
+        else:
+            print(f"Config list file not found: {config_list_path}")
+
+        # Generate test parameters
+        if config_files:
+            metafunc.parametrize(
+                "config_filename",
+                config_files,
+                ids=[config_file.stem for config_file in config_files],
+            )
+        else:
+            print("No config files found, test will be skipped")
@@ -0,0 +1,172 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""
+GPQA evaluation using vLLM server and GPT-OSS evaluation package.
+
+Usage:
+pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py \
+    --config-list-file=configs/models-h200.txt
+"""
+
+import os
+import shlex
+import subprocess
+import sys
+import urllib.request
+from pathlib import Path
+
+import regex as re
+import yaml
+
+from tests.utils import RemoteOpenAIServer
+
+TOL = 0.05  # Absolute tolerance for accuracy comparison
+
+# Path to tiktoken encoding files
+TIKTOKEN_DATA_DIR = Path(__file__).parent / "data"
+
+# Tiktoken encoding files to download
+TIKTOKEN_FILES = {
+    "cl100k_base.tiktoken": "https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken",
+    "o200k_base.tiktoken": "https://openaipublic.blob.core.windows.net/encodings/o200k_base.tiktoken",
+}
+
+
+def ensure_tiktoken_files():
+    """Download tiktoken encoding files if they don't exist."""
+    TIKTOKEN_DATA_DIR.mkdir(parents=True, exist_ok=True)
+
+    for filename, url in TIKTOKEN_FILES.items():
+        filepath = TIKTOKEN_DATA_DIR / filename
+        if not filepath.exists():
+            print(f"Downloading {filename} from {url}...")
+            urllib.request.urlretrieve(url, filepath)
+            print(f"  Downloaded to {filepath}")
+        else:
+            print(f"  {filename} already exists.")
+
+
+def run_gpqa_eval(model_name: str, base_url: str, reasoning_effort: str) -> float:
+    """Run GPQA evaluation using the gpt-oss evaluation package."""
+
+    # Build the command to run the evaluation
+    cmd = [
+        sys.executable,
+        "-m",
+        "gpt_oss.evals",
+        "--eval",
+        "gpqa",
+        "--model",
+        model_name,
+        "--reasoning-effort",
+        reasoning_effort,
+        "--base-url",
+        base_url,
+        "--n-threads",
+        "200",
+    ]
+
+    try:
+        # Set up environment for the evaluation subprocess
+        # Inherit current environment and add required variables
+        eval_env = os.environ.copy()
+        eval_env["OPENAI_API_KEY"] = "dummy"
+
+        # Run the evaluation
+        result = subprocess.run(
+            cmd,
+            text=True,
+            capture_output=True,
+            timeout=1800,  # 30 minute timeout
+            env=eval_env,
+        )
+
+        print("Evaluation process stdout:\n", result.stdout)
+        print("Evaluation process stderr:\n", result.stderr)
+        print(f"Evaluation process return code: {result.returncode}")
+
+        if result.returncode != 0:
+            raise RuntimeError(
+                f"Evaluation failed with exit code {result.returncode}:\n"
+                f"stdout: {result.stdout}\nstderr: {result.stderr}"
+            )
+
+        # Parse the output to extract the score
+        match = re.search(r"'metric':\s*([\d.]+)", result.stdout)
+        if match:
+            return float(match.group(1))
+
+        # If we still can't find it, raise an error
+        raise ValueError(
+            f"Could not parse score from evaluation output:\n{result.stdout}"
+        )
+
+    except subprocess.TimeoutExpired as e:
+        raise RuntimeError("Evaluation timed out") from e
+
+
+def test_gpqa_correctness(config_filename):
+    """Test GPQA correctness for a given model configuration."""
+    # Ensure tiktoken files are downloaded
+    ensure_tiktoken_files()
+
+    # Verify tiktoken files exist
+    for filename in TIKTOKEN_FILES:
+        filepath = TIKTOKEN_DATA_DIR / filename
+        assert filepath.exists(), f"Tiktoken file not found: {filepath}"
+
+    eval_config = yaml.safe_load(config_filename.read_text(encoding="utf-8"))
+
+    # Parse server arguments from config (use shlex to handle quoted strings)
+    server_args_str = eval_config.get("server_args", "")
+    server_args = shlex.split(server_args_str) if server_args_str else []
+
+    # Add standard server arguments
+    server_args.extend(
+        [
+            "--trust-remote-code",
+            "--enforce-eager",
+            "--disable-uvicorn-access-log",
+        ]
+    )
+
+    # Build server environment with tiktoken path and any config-specified vars
+    server_env = {"TIKTOKEN_ENCODINGS_BASE": str(TIKTOKEN_DATA_DIR)}
+    if eval_config.get("env"):
+        server_env.update(eval_config["env"])
+
+    reasoning_effort = eval_config.get("reasoning_effort", "low")
+
+    print(f"Starting GPQA evaluation for model: {eval_config['model_name']}")
+    print(f"Expected metric threshold: {eval_config['metric_threshold']}")
+    print(f"Reasoning effort: {reasoning_effort}")
+    print(f"Server args: {' '.join(server_args)}")
+    print(f"Server environment variables: {server_env}")
+
+    # Launch server and run evaluation
+    with RemoteOpenAIServer(
+        eval_config["model_name"],
+        server_args,
+        env_dict=server_env,
+        max_wait_seconds=eval_config.get("startup_max_wait_seconds", 1800),
+    ) as remote_server:
+        base_url = remote_server.url_for("v1")
+        print(f"Server started at: {base_url}")
+
+        measured_metric = run_gpqa_eval(
+            eval_config["model_name"], base_url, reasoning_effort
+        )
+        expected_metric = eval_config["metric_threshold"]
+
+        print(f"GPQA Results for {eval_config['model_name']}:")
+        print(f"  Measured metric: {measured_metric:.4f}")
+        print(f"  Expected metric: {expected_metric:.4f}")
+        print(f"  Tolerance: {TOL:.4f}")
+
+        # Verify metric is within tolerance
+        assert measured_metric >= expected_metric - TOL, (
+            f"GPQA metric too low: {measured_metric:.4f} < "
+            f"{expected_metric:.4f} - {TOL:.4f} = {expected_metric - TOL:.4f}"
+        )
+
+        print(f"GPQA test passed for {eval_config['model_name']}")
@@ -0,0 +1,40 @@
+# GSM8K Accuracy Evaluation
+
+This directory contains a replacement for the lm-eval-harness GSM8K evaluation, using an isolated GSM8K script and vLLM server for better performance and control.
+
+## Usage
+
+### Run tests with pytest (like buildkite)
+
+```bash
+pytest -s -v tests/evals/gsm8k/test_gsm8k_correctness.py \
+    --config-list-file=configs/models-small.txt
+```
+
+### Run standalone evaluation script
+
+```bash
+# Start vLLM server first
+vllm serve Qwen/Qwen2.5-1.5B-Instruct --port 8000
+
+# Run evaluation
+python tests/evals/gsm8k/gsm8k_eval.py --port 8000
+```
+
+## Configuration Format
+
+Model configs in `configs/` directory use this YAML format:
+
+```yaml
+model_name: "Qwen/Qwen2.5-1.5B-Instruct"
+accuracy_threshold: 0.54  # Minimum expected accuracy
+num_questions: 1319       # Number of questions (default: full test set)
+num_fewshot: 5            # Few-shot examples from train set
+server_args: "--max-model-len 4096 --tensor-parallel-size 2 --moe-backend flashinfer_cutlass"  # Server arguments
+env:                      # Environment variables (optional)
+  VLLM_LOGGING_LEVEL: "DEBUG"
+```
+
+The `server_args` field accepts any arguments that can be passed to `vllm serve`.
+
+The `env` field accepts a dictionary of environment variables to set for the server process.
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-R1"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --data-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,12 @@
+model_name: "deepseek-ai/DeepSeek-R1"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --data-parallel-size 8
+  --enable-expert-parallel
+  --attention-backend=TRITON_ATTN
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-R1"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,12 @@
+model_name: "deepseek-ai/DeepSeek-R1"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --attention-backend=TRITON_ATTN
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,6 @@
+model_name: "RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8"
+accuracy_threshold: 0.72
+num_questions: 1319
+num_fewshot: 5
+rocm_request_timeout_seconds: 1800
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-V3.2"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --data-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,12 @@
+model_name: "deepseek-ai/DeepSeek-V3.2"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --data-parallel-size 8
+  --enable-expert-parallel
+  --attention-backend=TRITON_ATTN
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,11 @@
+model_name: "deepseek-ai/DeepSeek-V3.2"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,12 @@
+model_name: "deepseek-ai/DeepSeek-V3.2"
+accuracy_threshold: 0.95
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --attention-backend=TRITON_ATTN
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
@@ -0,0 +1,15 @@
+model_name: "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic"
+accuracy_threshold: 0.84
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+use_chat_completions: true
+# Diffusion models use a fixed internal temperature schedule and do not
+# support per-request temperature or seed overrides.
+temperature: 1.0
+seed: null
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --attention-backend TRITON_ATTN
@@ -0,0 +1,5 @@
+model_name: "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test"
+accuracy_threshold: 0.74
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8"
+accuracy_threshold: 0.31
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,12 @@
+model_name: "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
+accuracy_threshold: 0.93
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --mamba-backend flashinfer
+  --speculative-config '{"method":"mtp","num_speculative_tokens":5}'
@@ -0,0 +1,11 @@
+model_name: "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"
+accuracy_threshold: 0.93
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 8
+  --enable-expert-parallel
+  --speculative-config '{"method":"mtp","num_speculative_tokens":5}'
@@ -0,0 +1,12 @@
+model_name: "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"
+accuracy_threshold: 0.93
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1200
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --enable-expert-parallel
+  --mamba-backend flashinfer
+  --speculative-config '{"method":"mtp","num_speculative_tokens":5}'
@@ -0,0 +1,6 @@
+model_name: "nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16"
+accuracy_threshold: 0.45
+num_questions: 1319
+num_fewshot: 5
+rocm_request_timeout_seconds: 1800
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
+accuracy_threshold: 0.60
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-0.6B-FP8"
+accuracy_threshold: 0.375
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: nm-testing/Qwen3-30B-A3B-MXFP4A16
+accuracy_threshold: 0.88
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: "nvidia/Qwen3-30B-A3B-FP4"
+accuracy_threshold: 0.89
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,6 @@
+model_name: "amd/Qwen3-30B-A3B-Thinking-2507-FP8"
+accuracy_threshold: 0.81
+num_questions: 1319
+num_fewshot: 5
+max_tokens: 1024
+server_args: "--max-model-len 4096 --gpu-memory-utilization 0.85"
@@ -0,0 +1,6 @@
+model_name: "amd/Qwen3-30B-A3B-Thinking-2507-PTPC-FP8"
+accuracy_threshold: 0.81
+num_questions: 1319
+num_fewshot: 5
+max_tokens: 1024
+server_args: "--max-model-len 4096 --gpu-memory-utilization 0.85"
@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-4B"
+accuracy_threshold: 0.78
+num_questions: 1319
+num_fewshot: 5
+server_args: "--kv-cache-dtype turboquant_k3v4_nc --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-4B"
+accuracy_threshold: 0.80
+num_questions: 1319
+num_fewshot: 5
+server_args: "--kv-cache-dtype turboquant_k8v4 --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-4B"
+accuracy_threshold: 0.75
+num_questions: 1319
+num_fewshot: 5
+server_args: "--kv-cache-dtype turboquant_3bit_nc --max-model-len 4096"
@@ -0,0 +1,5 @@
+model_name: "Qwen/Qwen3-4B"
+accuracy_threshold: 0.80
+num_questions: 1319
+num_fewshot: 5
+server_args: "--kv-cache-dtype turboquant_4bit_nc --max-model-len 4096"
@@ -0,0 +1,11 @@
+model_name: "nm-testing/Qwen3-Next-80B-A3B-Instruct-NVFP4"
+accuracy_threshold: 0.75
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --enable-expert-parallel
+  --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":1}'
+  --moe-backend=flashinfer_trtllm
@@ -0,0 +1,10 @@
+model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --enable-expert-parallel
+  --async-scheduling
+  --moe-backend=flashinfer_trtllm
@@ -0,0 +1,9 @@
+model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
+accuracy_threshold: 0.85
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --enable-expert-parallel
+  --async-scheduling
@@ -0,0 +1,10 @@
+model_name: "Qwen/Qwen3.5-35B-A3B"
+accuracy_threshold: 0.84
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --data-parallel-size 2
+  --enable-expert-parallel
+  --no-enable-flashinfer-autotune
@@ -0,0 +1,10 @@
+model_name: "Qwen/Qwen3.5-35B-A3B-FP8"
+accuracy_threshold: 0.79
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --data-parallel-size 2
+  --enable-expert-parallel
+  --kv-cache-dtype fp8
@@ -0,0 +1,13 @@
+model_name: "amd/Qwen3.5-35B-A3B-MXFP4"
+accuracy_threshold: 0.89
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --gpu-memory-utilization 0.35
+  --moe-backend aiter
+env:
+  VLLM_ROCM_USE_AITER: "1"
+  ENABLE_CK: "0"  # Avoid AITER CK-based MHA JIT compilation to save time
@@ -0,0 +1,11 @@
+model_name: "amd/Qwen3.5-35B-A3B-MXFP4"
+accuracy_threshold: 0.89
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+startup_max_wait_seconds: 1800
+server_args: >-
+  --max-model-len 4096
+  --tensor-parallel-size 2
+  --moe-backend emulation
+  --gpu-memory-utilization 0.35
@@ -0,0 +1,12 @@
+model_name: "nvidia/Qwen3.5-397B-A17B-NVFP4"
+accuracy_threshold: 0.88
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --data-parallel-size 2
+  --enable-expert-parallel
+  --max-num-seqs 384
+  --spec-method mtp
+  --spec-tokens 3
@@ -0,0 +1,10 @@
+model_name: "nvidia/Qwen3.5-397B-A17B-NVFP4"
+accuracy_threshold: 0.88
+tolerance: 0.03
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --max-model-len 4096
+  --data-parallel-size 2
+  --enable-expert-parallel
+  --max-num-seqs 512
@@ -0,0 +1,5 @@
+model_name: "google/gemma-4-E4B-it-qat-mobile-ct"
+accuracy_threshold: 0.50
+num_questions: 1319
+num_fewshot: 5
+server_args: "--enforce-eager --max-model-len 4096"
@@ -0,0 +1,10 @@
+model_name: "nm-testing/Qwen2-1.5B-Instruct-FP8W8"
+accuracy_threshold: 0.55
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,8 @@
+model_name: "nm-testing/Qwen2-1.5B-Instruct-FP8W8"
+accuracy_threshold: 0.55
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --linear-backend humming
@@ -0,0 +1,10 @@
+model_name: "mgoin/Qwen3-0.6B-MXFP8"
+accuracy_threshold: 0.39
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,8 @@
+model_name: "mgoin/Qwen3-0.6B-MXFP8"
+accuracy_threshold: 0.39
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --linear-backend humming
@@ -0,0 +1,13 @@
+model_name: "QuixiAI/Qwen3-30B-A3B-AWQ"
+accuracy_threshold: 0.90
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+  --dtype bfloat16
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,13 @@
+model_name: "QuixiAI/Qwen3-30B-A3B-AWQ"
+accuracy_threshold: 0.90
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+  --dtype bfloat16
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"int8"}'
@@ -0,0 +1,11 @@
+model_name: "QuixiAI/Qwen3-30B-A3B-AWQ"
+accuracy_threshold: 0.90
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+  --dtype bfloat16
@@ -0,0 +1,11 @@
+model_name: "nm-testing/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,9 @@
+model_name: "nm-testing/Qwen3-30B-A3B-FP8-block"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
@@ -0,0 +1,11 @@
+model_name: "nm-testing/Qwen3-30B-A3B-Fp8-v1"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,9 @@
+model_name: "nm-testing/Qwen3-30B-A3B-Fp8-v1"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
@@ -0,0 +1,11 @@
+model_name: "Qwen/Qwen3-30B-A3B-GPTQ-Int4"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,11 @@
+model_name: "Qwen/Qwen3-30B-A3B-GPTQ-Int4"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"int8"}'
@@ -0,0 +1,9 @@
+model_name: "Qwen/Qwen3-30B-A3B-GPTQ-Int4"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
@@ -0,0 +1,11 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w8a8"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"int8"}'
@@ -0,0 +1,9 @@
+model_name: "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w8a8"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
@@ -0,0 +1,11 @@
+model_name: "nm-testing/Qwen3-30B-A3B-MXFP4A16"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --quantization humming
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,9 @@
+model_name: "nm-testing/Qwen3-30B-A3B-MXFP4A16"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --quantization humming
+  --linear-backend humming
@@ -0,0 +1,9 @@
+model_name: "nvidia/Qwen3-30B-A3B-NVFP4"
+accuracy_threshold: 0.86
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
@@ -0,0 +1,13 @@
+model_name: "Qwen/Qwen3-30B-A3B"
+accuracy_threshold: 0.80
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --tensor-parallel-size 1
+  --quantization humming
+  --kernel-config.enable_flashinfer_autotune=False
+env:
+  VLLM_HUMMING_ONLINE_QUANT_CONFIG: '{"dtype":"int5","hadamard_block_size":-1}'
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,13 @@
+model_name: "Qwen/Qwen3-30B-A3B"
+accuracy_threshold: 0.80
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --tensor-parallel-size 1
+  --quantization humming
+  --kernel-config.enable_flashinfer_autotune=False
+env:
+  VLLM_HUMMING_ONLINE_QUANT_CONFIG: '{"dtype":"int5","hadamard_block_size":-1}'
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"int8"}'
@@ -0,0 +1,12 @@
+model_name: "Qwen/Qwen3-30B-A3B"
+accuracy_threshold: 0.80
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --tensor-parallel-size 1
+  --quantization humming
+  --kernel-config.enable_flashinfer_autotune=False
+env:
+  VLLM_HUMMING_ONLINE_QUANT_CONFIG: '{"dtype":"int5","hadamard_block_size":-1}'
@@ -0,0 +1,12 @@
+model_name: "Qwen/Qwen3.5-35B-A3B-FP8"
+accuracy_threshold: 0.90
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,10 @@
+model_name: "Qwen/Qwen3.5-35B-A3B-FP8"
+accuracy_threshold: 0.90
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
@@ -0,0 +1,12 @@
+model_name: "Qwen/Qwen3.5-35B-A3B"
+accuracy_threshold: 0.90
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --quantization experts_int8
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"int8"}'
@@ -0,0 +1,10 @@
+model_name: "Qwen/Qwen3.5-35B-A3B"
+accuracy_threshold: 0.90
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --quantization experts_int8
@@ -0,0 +1,10 @@
+model_name: "RedHatAI/Qwen3.5-4B-quantized.w4a16"
+accuracy_threshold: 0.82
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,11 @@
+model_name: "RedHatAI/Qwen3.5-4B-quantized.w4a16"
+accuracy_threshold: 0.82
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --linear-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"int8"}'
@@ -0,0 +1,9 @@
+model_name: "RedHatAI/Qwen3.5-4B-quantized.w4a16"
+accuracy_threshold: 0.82
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --linear-backend humming
@@ -0,0 +1,10 @@
+model_name: "RedHatAI/Qwen3.6-35B-A3B-NVFP4"
+accuracy_threshold: 0.91
+num_questions: 1319
+num_fewshot: 5
+gen_prefix: " <think>\n\n</think>\n"
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+  --linear-backend humming
@@ -0,0 +1,9 @@
+gpt-oss-20b-humming-act-fp8.yaml
+Qwen3-30B-A3B-MXFP4A16-humming-act-fp8.yaml
+Qwen2-1.5B-Instruct-FP8W8-humming-act-fp8.yaml
+Qwen3-0.6B-MXFP8-humming-act-fp8.yaml
+Qwen3-30B-A3B-Fp8-v1-humming-act-fp8.yaml
+Qwen3-30B-A3B-FP8-block-humming-act-fp8.yaml
+Qwen3-30B-A3B-GPTQ-Int4-humming-act-fp8.yaml
+Qwen3-30B-A3B-AWQ-humming.yaml
+Qwen3.5-35B-A3B-FP8-humming-act-fp8.yaml
@@ -0,0 +1,4 @@
+Qwen3-30B-A3B-Instruct-2507-quantized.w8a8-humming-act-int8.yaml
+Qwen3-30B-A3B-GPTQ-Int4-humming-act-int8.yaml
+Qwen3-30B-A3B-AWQ-humming.yaml
+Qwen3.5-35B-A3B-experts-int8-humming-act-int8.yaml
@@ -0,0 +1,3 @@
+Qwen3-30B-A3B-int5wc-hadamard-humming.yaml
+Qwen3-30B-A3B-int5wc-hadamard-humming-act-fp8.yaml
+Qwen3-30B-A3B-int5wc-hadamard-humming-act-int8.yaml
@@ -0,0 +1,13 @@
+gpt-oss-20b-humming.yaml
+Qwen3-30B-A3B-MXFP4A16-humming.yaml
+Qwen2-1.5B-Instruct-FP8W8-humming.yaml
+Qwen3-0.6B-MXFP8-humming.yaml
+Qwen3.6-35B-A3B-NVFP4-humming.yaml
+Qwen3-30B-A3B-Fp8-v1-humming.yaml
+Qwen3-30B-A3B-FP8-block-humming.yaml
+Qwen3-30B-A3B-GPTQ-Int4-humming.yaml
+Qwen3-30B-A3B-Instruct-2507-quantized.w8a8-humming.yaml
+Qwen3-30B-A3B-NVFP4-humming.yaml
+Qwen3-30B-A3B-AWQ-humming.yaml
+Qwen3.5-35B-A3B-FP8-humming.yaml
+Qwen3.5-35B-A3B-experts-int8-humming.yaml
@@ -0,0 +1,10 @@
+model_name: "openai/gpt-oss-20b"
+accuracy_threshold: 0.30
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
+env:
+  VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'
@@ -0,0 +1,8 @@
+model_name: "openai/gpt-oss-20b"
+accuracy_threshold: 0.30
+num_questions: 1319
+num_fewshot: 5
+server_args: >-
+  --enforce-eager
+  --max-model-len 8192
+  --moe-backend humming
@@ -0,0 +1,3 @@
+Qwen3-Next-80B-A3B-NVFP4-EP2.yaml
+Qwen3-Next-FP8-EP2.yaml
+Nemotron-3-Super-120B-A12B-NVFP4.yaml
@@ -0,0 +1,5 @@
+Qwen3-0.6B-FP8.yaml
+Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
+Qwen1.5-MoE-W4A16-CT.yaml
+DeepSeek-V2-Lite-Instruct-FP8.yaml
+Qwen3-30B-A3B-NVFP4.yaml
@@ -0,0 +1,6 @@
+DeepSeek-R1-TP.yaml
+DeepSeek-R1-DP.yaml
+DeepSeek-V3.2-TP.yaml
+DeepSeek-V3.2-DP.yaml
+Nemotron-3-Super-120B-A12B-BF16.yaml
+Nemotron-3-Super-120B-A12B-FP8.yaml
@@ -0,0 +1,7 @@
+Qwen3-0.6B-FP8.yaml
+Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
+Qwen1.5-MoE-W4A16-CT.yaml
+DeepSeek-V2-Lite-Instruct-FP8.yaml
+Qwen3-Next-FP8-EP2_MI355.yaml
+Qwen3-30B-A3B-Thinking-2507-FP8.yaml
+Qwen3-30B-A3B-Thinking-2507-PTPC-FP8.yaml
@@ -0,0 +1,7 @@
+DeepSeek-R1-TP_MI325.yaml
+DeepSeek-R1-DP_MI325.yaml
+DeepSeek-V3.2-TP_MI325.yaml
+DeepSeek-V3.2-DP_MI325.yaml
+Qwen3-30B-A3B-NVFP4.yaml
+Qwen3.5-35B-A3B-MXFP4-AITER-TP2.yaml
+Qwen3.5-35B-A3B-MXFP4-EMU-TP2.yaml
@@ -0,0 +1,4 @@
+Qwen3.5-35B-A3B-DEP2.yaml
+Qwen3.5-35B-A3B-FP8-DEP2.yaml
+Qwen3.5-397B-A17B-NVFP4-DEP2.yaml
+Qwen3.5-397B-A17B-NVFP4-DEP2-MTP.yaml
--- a/Show More
+++ b/Show More