diff --git a/docs/common/system-setup.md b/docs/common/system-setup.md
index d956c97..b5cea53 100644
--- a/docs/common/system-setup.md
+++ b/docs/common/system-setup.md
@@ -24,5 +24,5 @@ Basic checks (consult ROCm docs for expanded diagnostics):
 cat /opt/rocm/.info/version
 
 # Validate installed version
-amd-smi --version
+amd-smi version
 ```
diff --git a/docs/common/system-validation.md b/docs/common/system-validation.md
index 1180e01..bf49b1b 100644
--- a/docs/common/system-validation.md
+++ b/docs/common/system-validation.md
@@ -612,6 +612,11 @@ Pass if bus bandwidth (large message, ~8 GB) ≥ 304 GB/s.
 
 ### rocBLAS GEMM Benchmarks
 
+For installation, review rocBLAS documentation:
+
+- [Linux installation](https://rocm.docs.amd.com/projects/rocBLAS/en/latest/install/Linux_Install_Guide.html)
+- [Windows installation](https://rocm.docs.amd.com/projects/rocBLAS/en/latest/install/Windows_Install_Guide.html)
+
 Run each until peak (stable) TFLOPS observed. Capture highest achieved value.
 
 FP32:
@@ -696,7 +701,7 @@ For complete details, extended guidance, and troubleshooting tips, consult the *
 
 ### AGFHC Installation
 
-For AGFHC installation steps consult the AMD GPU Field Health Check (AGFHC) User Guide (UG-58416) on the [AMD Technical Information Portal](https://docs.amd.com/).
+Reach out to your AMD customer success team for specific installation steps regarding AGFHC.
 
 The ROCm Validation suite (RVS) is a prerequisite of AGFHC. Make sure that this is installed as of the ROCm software installation. For example, on Ubuntu:
 
@@ -832,9 +837,8 @@ The tables below list the recommended and suggested AGFHC validation recipes alo
 | gfx_lvl4 | All AMD MI3xx Instinct™ models | 1 Hour | GPU stress test to hot spot test GPU needed for DLC systems |
 | sleep 300 sec. | | 5 Minutes, sixth iteration | For silicon to contract to widen any cracks |
 | minihpl | All AMD MI3xx Instinct™ models | 3 Hours | Search for voltage failures and stress HBM |
-| xgmi_lvl1 | All AMD MI3xx Instinct™ models | 5 Minutes | Check for link degradation |
 | pcie_lvl2 | All AMD MI3xx Instinct™ models | 10 Minutes | Check for link degradation |
-| Total | | | 14 Hours and 45 Minutes |
+| Total | | | 14 Hours and 40 Minutes |
 
 #### Recommended AGFHC Tests
 
diff --git a/docs/conf.py b/docs/conf.py
index faf1c83..713f896 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -2,6 +2,8 @@
 import os
 import subprocess
 import sys
+from pathlib import Path
+import shutil
 
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "instinct.docs.amd.com")
 html_context = {}
@@ -24,6 +26,7 @@
 html_theme_options = {
     "flavor": "instinct",
     "link_main_doc": True,
+    "use_download_button": True,
     "nav_secondary_items": {
         "Community": "https://github.com/ROCm/ROCm/discussions",
         "Blogs": "https://rocm.blogs.amd.com/",
@@ -38,5 +41,238 @@
 external_toc_path = "./sphinx/_toc.yml"
 
 exclude_patterns = ['.venv']
+
 # Add anchors to headings up to level 4
-myst_heading_anchors = 4
\ No newline at end of file
+myst_heading_anchors = 4
+
+html_extra_path = ["llms.txt"]
+
+import re
+
+EXCLUDED_DIRS = {
+    "_build",
+    "_templates",
+    "_static",
+    ".git",
+    ".venv",
+}
+
+EXCLUDED_FILES = {
+    "notices.md",
+}
+
+MARKUP_PREFIXES = (
+    ":::",
+    "```{",
+    "```",
+    ":img-top:",
+    ":class",
+    ":link:",
+    ":link-type:",
+    ":shadow:",
+    ":columns:",
+    ":padding:",
+    ":gutter:",
+    ":open:",
+    ":name:",
+    ":header-rows:",
+    ":alt:",
+    "+++",
+    "-->",
+    "{bdg-",
+)
+
+# Matches lines like "align: center", "alt:", "name: foo" (directive options
+# not starting with a colon, common in MyST figure/table fences)
+_BARE_DIRECTIVE_RE = re.compile(r"^[a-z][a-z_-]*:\s*\S*$")
+
+# Matches MyST/RST anchor labels like "(gpu-arch-documentation)="
+_ANCHOR_LABEL_RE = re.compile(r"^\(\w[\w-]*\)=$")
+
+# Matches RST section underlines (e.g. "====", "----", "~~~~")
+_RST_UNDERLINE_RE = re.compile(r"^[=\-~^\"\'#*+]{3,}$")
+
+# Matches RST code block directives (e.g. ".. code-block:: cpp", ".. code:: sh")
+_RST_CODE_BLOCK_RE = re.compile(r"^\.\.\s+(code-block|code|sourcecode)::")
+
+# Matches markdown table separator rows (e.g. "|---|---|", "| :--- | ---: |").
+_MD_TABLE_SEP_RE = re.compile(r"^\|[\s|:\-]+\|$")
+
+# Matches RST directives whose indented body should be discarded (e.g. raw HTML).
+_RST_SKIP_BLOCK_RE = re.compile(r"^\.\.\s+raw::")
+
+# Matches HTML tags (e.g. "<div>", "</p>", "<!--") but NOT RST hyperlink URL
+# continuation lines (e.g. "<https://...>`_").  The negative lookahead excludes
+# URL schemes so that multi-line RST inline hyperlinks are preserved.
+_HTML_TAG_RE = re.compile(r"^<(?!https?://|ftp://|mailto:)[a-zA-Z/!]")
+
+# Matches trailing HTML close tags at the end of a prose line
+# (e.g. "Browse blogs.</p>", "See the guide.</li></ul>").
+_TRAILING_HTML_CLOSE_RE = re.compile(r"(</[a-zA-Z]+>)+\s*$")
+
+MIN_PROSE_LINES = 10
+
+
+def should_skip(path: Path) -> bool:
+    return (
+        any(part in EXCLUDED_DIRS for part in path.parts)
+        or path.name in EXCLUDED_FILES
+    )
+
+
+def is_prose_line(line: str) -> bool:
+    stripped = line.strip()
+    if not stripped:
+        return False
+    if stripped.startswith(MARKUP_PREFIXES):
+        return False
+    # Drop bare directive-option lines (e.g. "align: center", "alt:")
+    if _BARE_DIRECTIVE_RE.match(stripped):
+        return False
+    # Drop MyST/RST anchor labels (e.g. "(gpu-arch-documentation)=")
+    if _ANCHOR_LABEL_RE.match(stripped):
+        return False
+    # Drop markdown table separator rows (e.g. "|---|---|", "| :--- | ---: |")
+    if _MD_TABLE_SEP_RE.match(stripped):
+        return False
+    # Drop HTML tags (e.g. "<div>", "</p>") but keep RST hyperlink URL
+    # continuation lines (e.g. "<https://rocm.docs.amd.com/...>`_")
+    if _HTML_TAG_RE.match(stripped):
+        return False
+    # Drop RST directives, comments, hyperlink targets, and substitution definitions
+    if stripped.startswith(".."):
+        return False
+    # Drop YAML frontmatter key-value pairs (e.g. "description lang=en": "text")
+    if stripped.startswith('"') and re.match(r'^"[^"]+"\s*:', stripped):
+        return False
+    # Drop RST field list items (e.g. ":type: int") and extended RST meta
+    # options (e.g. ":description lang=en: text"). Excludes inline roles at line
+    # start (e.g. ":cpp:func:`hipMalloc` returns..." or ":ref:`foo <bar>` describes...")
+    # because those are followed by a backtick, not a space or end-of-line.
+    if re.match(r"^:[A-Za-z][A-Za-z0-9_ =-]*:(\s|$)", stripped):
+        return False
+    # Drop RST section underlines (e.g. "====", "----", "~~~~")
+    if _RST_UNDERLINE_RE.match(stripped):
+        return False
+    return True
+
+
+def generate_combined_markdown(app, exception):
+    if exception:
+        return
+
+    docs_root = Path(app.srcdir)
+    output_file = Path(app.outdir) / "llms-full.txt"
+    base_file = docs_root / "llms.txt"
+
+    combined = []
+
+    if base_file.exists():
+        base_text = base_file.read_text(encoding="utf-8").rstrip().rstrip("-").rstrip()
+        combined.append(base_text)
+    else:
+        combined.append("# AMD Instinct Customer Acceptance Guide")
+
+    all_files = sorted(
+        list(docs_root.rglob("*.md")) + list(docs_root.rglob("*.rst"))
+    )
+
+    for doc_file in all_files:
+        if should_skip(doc_file):
+            continue
+
+        if doc_file == base_file:
+            continue
+
+        try:
+            content = doc_file.read_text(encoding="utf-8")
+        except Exception:
+            continue
+
+        lines = content.splitlines()
+        prose_lines = [line for line in lines if is_prose_line(line)]
+
+        if len(prose_lines) < MIN_PROSE_LINES:
+            continue
+
+        relative = doc_file.relative_to(docs_root)
+        in_backtick_fence = False
+        in_rst_code_block = False
+        in_rst_skip_block = False
+        in_html_comment = False  # inside <!-- ... --> block
+        in_html_open_tag = False  # inside a multi-line HTML opening tag
+        kept = []
+        for line in lines:
+            stripped = line.strip()
+            # Backtick fences (MyST/Markdown)
+            if stripped.startswith("```"):
+                in_backtick_fence = not in_backtick_fence
+                kept.append(line)
+                continue
+            if in_backtick_fence:
+                kept.append(line)
+                continue
+            # HTML comment block (<!-- ... -->): discard all content until -->
+            if in_html_comment:
+                if "-->" in stripped:
+                    in_html_comment = False
+                continue
+            # RST skip block (e.g. .. raw::): discard all indented content
+            if in_rst_skip_block:
+                if not stripped or line[0] in (" ", "\t"):
+                    continue
+                in_rst_skip_block = False
+            # RST code block: exit when a non-blank, non-indented line appears
+            if in_rst_code_block:
+                if not stripped or line[0] in (" ", "\t"):
+                    kept.append(line)
+                    continue
+                in_rst_code_block = False
+            # RST raw block: enter and discard both the directive and its body
+            if _RST_SKIP_BLOCK_RE.match(stripped):
+                in_rst_skip_block = True
+                continue
+            # RST code block: enter on directive line (directive itself is dropped)
+            if _RST_CODE_BLOCK_RE.match(stripped):
+                in_rst_code_block = True
+                continue
+            # HTML comment open (<!-- ... -->): discard opener and enter state
+            if stripped.startswith("<!--"):
+                if "-->" not in stripped:
+                    in_html_comment = True
+                continue
+            # Multi-line HTML opening tag: skip continuation lines until >
+            if in_html_open_tag:
+                if ">" in stripped:
+                    in_html_open_tag = False
+                continue
+            # Detect HTML opening tags that wrap across lines (no > on this line)
+            if _HTML_TAG_RE.match(stripped) and ">" not in stripped:
+                in_html_open_tag = True
+                continue
+            if not stripped:
+                kept.append(line)
+            elif is_prose_line(line):
+                # Strip trailing HTML close tags (e.g. "See the guide.</p>")
+                cleaned = _TRAILING_HTML_CLOSE_RE.sub("", line).rstrip()
+                cleaned_stripped = cleaned.strip()
+                if not cleaned_stripped:
+                    # Entire line was HTML close tags — keep original (shouldn't
+                    # normally reach here since _is_prose_line filters HTML).
+                    kept.append(line)
+                elif re.search(r"\w", cleaned_stripped):
+                    # Line has real word content after stripping close tags.
+                    kept.append(cleaned)
+                # else: only punctuation remains (e.g. bare ".") — discard.
+        cleaned = "\n".join(kept)
+
+        combined.append(f"\n\n---\n\n# {relative}\n")
+        combined.append(cleaned.strip())
+
+    output_file.write_text(
+        "\n".join(combined) + "\n",
+        encoding="utf-8",
+    )
+
+def setup(app):
+    app.connect("build-finished", generate_combined_markdown)
diff --git a/docs/gpus/mi300x.md b/docs/gpus/mi300x.md
index b20a089..cfc95b8 100644
--- a/docs/gpus/mi300x.md
+++ b/docs/gpus/mi300x.md
@@ -152,12 +152,12 @@ Performance validation ensures the system meets MI300X specifications. For detai
 
 ```bash
 rocblas-bench -f gemm \
-  -r s -m 4000 \
+  -r s -m 4000 -n 4000 -k 4000 \
   --lda 4000 --ldb 4000 --ldc 4000 \
   --transposeA N --transposeB T
 ```
 
-**Pass:** ≥ 94100 TFLOPS  
+**Pass:** ≥ 94100 GFLOPS  
 +++
 **Fail:** otherwise
 :::
@@ -179,7 +179,7 @@ rocblas-bench -f gemm_strided_batched_ex \
   --batch_count 5
 ```
 
-**Pass:** ≥ 130600 TFLOPS
+**Pass:** ≥ 130600 GFLOPS
 +++
 **Fail:** otherwise
 :::
@@ -201,7 +201,7 @@ rocblas-bench -f gemm_strided_batched_ex \
   --batch_count 5
 ```
 
-**Pass:** ≥ 162700 TFLOPS
+**Pass:** ≥ 162700 GFLOPS
 +++
 **Fail:** otherwise
 :::
@@ -210,15 +210,14 @@ rocblas-bench -f gemm_strided_batched_ex \
 [BabelStream](../common/system-validation.md#babelstream)
 ^^^
 
-| Copy # | Threshold (MB/s) |
+| Kernel | Threshold (MB/s) |
 |--------|-----------------|
-| 1 | ≥ 4,177,285 |
-| 2 | ≥ 4,067,069 |
-| 3 | ≥ 3,920,853 |
-| 4 | ≥ 3,885,301 |
-| 5 | ≥ 3,660,781 |
+| Copy  | ≥ 4,177,285 |
+| Mul   | ≥ 4,067,069 |
+| Add   | ≥ 3,920,853 |
+| Triad | ≥ 3,885,301 |
+| Dot   | ≥ 3,660,781 |
 
-**Pass:** Greater than or equal to 162700 TFLOPS
 +++
 **Fail:** otherwise
 :::
diff --git a/docs/gpus/mi325x.md b/docs/gpus/mi325x.md
index 67cfb58..41b6112 100644
--- a/docs/gpus/mi325x.md
+++ b/docs/gpus/mi325x.md
@@ -151,12 +151,12 @@ Performance validation ensures the system meets MI325X specifications. For detai
 
 ```bash
 rocblas-bench -f gemm \
-  -r s -m 4000 \
+  -r s -m 4000 -n 4000 -k 4000 \
   --lda 4000 --ldb 4000 --ldc 4000 \
   --transposeA N --transposeB T
 ```
 
-**Pass:** ≥ 94100 TFLOPS  
+**Pass:** ≥ 94100 GFLOPS  
 +++
 **Fail:** otherwise
 :::
@@ -178,7 +178,7 @@ rocblas-bench -f gemm_strided_batched_ex \
   --batch_count 5
 ```
 
-**Pass:** ≥ 130600 TFLOPS
+**Pass:** ≥ 130600 GFLOPS
 +++
 **Fail:** otherwise
 :::
@@ -200,7 +200,7 @@ rocblas-bench -f gemm_strided_batched_ex \
   --batch_count 5
 ```
 
-**Pass:** ≥ 162700 TFLOPS
+**Pass:** ≥ 162700 GFLOPS
 +++
 **Fail:** otherwise
 :::
diff --git a/docs/gpus/mi350x.md b/docs/gpus/mi350x.md
index 1dcea18..6385fd8 100644
--- a/docs/gpus/mi350x.md
+++ b/docs/gpus/mi350x.md
@@ -52,18 +52,20 @@ Example (truncated for brevity – expect 8 lines):
 f5:00.0 Processing accelerators: Advanced Micro Devices, Inc. [AMD/ATI] Device 75a0
 ```
 
-## Acceptance Criteria
+## Acceptance Criteria Checklist
 
-The MI350X system acceptance process validates that the platform is correctly configured, stable, and performing to expectations. Follow the sequence: Prerequisites → Basic Health Checks → System Validation (AGFHC recipes) → Performance Benchmarks.
-
-### System Acceptance Process
+This section presents the high-level cluster acceptance validation criteria in a clear, checklist-driven format designed to enable efficient execution and tracking. The checklist is used to verify that the system meets all required technical, operational, and performance criteria necessary to achieve "Go-Live" readiness. It is organized into the following key areas:
 
 1. **[Prerequisites Validation](#prerequisites-validation)** - Ensure all system requirements and dependencies are met
 2. **[Basic Health Checks](#basic-health-checks)** - Verify hardware detection and basic system health
-3. **[System Validation](#system-validation)** - Conduct comprehensive stress testing and qualification
+3. **[System Validation](#system-validation)** - Conduct comprehensive single and multi-node stress testing and qualification
 4. **[Performance Benchmarks](#performance-benchmarks)** - Validate compute, memory, and interconnect performance
 
-System is accepted when all required recipe runs and benchmarks pass without errors and no hardware faults appear in logs.
+Each area consists of a defined set of criteria that are hyperlinked to the corresponding sections within this guide, enabling users to quickly access detailed procedures, execution steps, and supporting guidance.
+
+The System Validation area, which includes both single-node and multi-node testing, defines minimum required execution (run) times for each test. These requirements ensure that validation is conducted under appropriate conditions to accurately assess system stability, performance, and reliability.
+
+Successful completion of this checklist, with no errors or hardware faults observed in validation logs, confirms that the cluster has been properly configured, validated at both the single-node and multi-node levels, and is capable of supporting sustained AI workloads in a production environment.
 
 ### Prerequisites Validation
 
@@ -101,12 +103,29 @@ These checks ensure fundamental system health and proper GPU detection. For deta
 
 AGFHC (AMD GPU Field Health Check) provides structured recipes exercising PCIe, HBM, compute, power/thermal and fabric.
 
-| Recipe | Command | Purpose | Pass Criteria |
-|--------|---------|---------|---------------|
-| [all_lvl5](../common/system-validation.md#all_lvl5) | `/opt/amd/agfhc/agfhc -r all_lvl5 -o <output_dir>` | Broad ~2h system-level coverage (PCIe, HBM, compute, power) | Overall result PASS / return code 0 |
-| [hbm_lvl5](../common/system-validation.md#hbm_lvl5) (run twice) | `/opt/amd/agfhc/agfhc -r hbm_lvl5:i=2 -o <output_dir>` | Intensive HBM stress & ECC observation | Both iterations PASS / no memory errors |
-| [pcie_lvl2](../common/system-validation.md#pcie_lvl2) | `/opt/amd/agfhc/agfhc -r pcie_lvl2 -o <output_dir>` | PCIe bandwidth & link health | PASS / expected link stability |
-| [miniHPL](../common/system-validation.md#minihpl) (optional) | `/opt/amd/agfhc/agfhc -t miniHPL:d=120m -o <output_dir>` | Linpack-like integration stress (MI350X) | PASS / completes without failures |
+#### Single-Node Tests
+
+Following single-node tests must be performed at the required run time with no failures reported in validation logs.
+
+| Test | Command | Run Time | Purpose | Pass Criteria |
+|--------|---------|----------|---------|---------------|
+| [all_lvl5](../common/system-validation.md#all_lvl5) | `/opt/amd/agfhc/agfhc -r all_lvl5 -o <output_dir>` | 2 hours | Broad system-level coverage (PCIe, HBM, compute, power) | Overall result PASS / return code 0 |
+| [hbm_lvl5](../common/system-validation.md#hbm_lvl5) (4 iterations) | `/opt/amd/agfhc/agfhc -r hbm_lvl5:i=4 -o <output_dir>` | 8 hours | Intensive HBM stress & ECC observation | All iterations PASS / no memory errors |
+| [gfx_lvl4](../common/system-validation.md#gfx_lvl4) | `/opt/amd/agfhc/agfhc -r gfx_lvl4 -o <output_dir>` | 1 hour | GPU compute stress test | PASS / return code 0 |
+| [miniHPL](../common/system-validation.md#minihpl) | `/opt/amd/agfhc/agfhc -t minihpl:d=3h -o <output_dir>` | 3 hours (10 hours recommended) | Linpack-like integration stress | PASS / completes without failures |
+| [pcie_lvl2](../common/system-validation.md#pcie_lvl2) | `/opt/amd/agfhc/agfhc -r pcie_lvl2 -o <output_dir>` | 10 minutes | PCIe bandwidth & link health | PASS / expected link stability |
+| [Single-node RCCL](../common/rccl-benchmarking.md#single-node-rccl-testing) | `all_reduce_perf -b 8 -e 8G -f 2 -g 8` | 2–11 minutes | Single-node GPU interconnect validation | busbw meets expected thresholds |
+| [AI Workloads](../network/validation.md#ai-workload-validation-with-the-cluster-validation-suite) | See workload validation | 1–24 hours | Sustained AI workload (Llama 3.1 70B with JAX) | Completes without failures |
+
+#### Multi-Node Tests
+
+Following multi-node tests must be performed at the required run time with no failures reported in validation logs.
+
+| Test | Reference | Run Time | Purpose | Pass Criteria |
+|------|-----------|----------|---------|---------------|
+| [OFED Performance Tests](../network/rdma-benchmarking.md#ofed-performance-tests) | Network validation | 2 hours | RDMA fabric bandwidth and latency | All tests PASS / expected bandwidth |
+| [Multi-node RCCL](../network/validation.md#rccl-multi-node-fabric-test) | Network validation | Up to 128 nodes, 10 hours | Multi-node GPU fabric validation | All nodes PASS / expected bandwidth |
+| [AI Workloads](../network/validation.md#ai-workload-validation-with-the-cluster-validation-suite) | Cluster validation | 24 hours | Sustained AI workload (Llama 3.1 405B with JAX) | Completes without failures |
 
 Review `results.json` in the output directory or terminal summary; any FAIL requires remediation before acceptance.
 
diff --git a/docs/gpus/mi355x.md b/docs/gpus/mi355x.md
index 6bb4ed6..5e54af1 100644
--- a/docs/gpus/mi355x.md
+++ b/docs/gpus/mi355x.md
@@ -52,18 +52,20 @@ Example (truncated for brevity – expect 8 lines):
 f5:00.0 Processing accelerators: Advanced Micro Devices, Inc. [AMD/ATI] Device 75a3
 ```
 
-## Acceptance Criteria
+## Acceptance Criteria Checklist
 
-The MI355X system acceptance process validates that the platform is correctly configured, stable, and performing to expectations. Follow the sequence: Prerequisites → Basic Health Checks → System Validation (AGFHC recipes) → Performance Benchmarks.
-
-### System Acceptance Process
+This section presents the high-level cluster acceptance validation criteria in a clear, checklist-driven format designed to enable efficient execution and tracking. The checklist is used to verify that the system meets all required technical, operational, and performance criteria necessary to achieve "Go-Live" readiness. It is organized into the following key areas:
 
 1. **[Prerequisites Validation](#prerequisites-validation)** - Ensure all system requirements and dependencies are met
 2. **[Basic Health Checks](#basic-health-checks)** - Verify hardware detection and basic system health
-3. **[System Validation](#system-validation)** - Conduct comprehensive stress testing and qualification
+3. **[System Validation](#system-validation)** - Conduct comprehensive single and multi-node stress testing and qualification
 4. **[Performance Benchmarks](#performance-benchmarks)** - Validate compute, memory, and interconnect performance
 
-System is accepted when all required recipe runs and benchmarks pass without errors and no hardware faults appear in logs.
+Each area consists of a defined set of criteria that are hyperlinked to the corresponding sections within this guide, enabling users to quickly access detailed procedures, execution steps, and supporting guidance.
+
+The System Validation area, which includes both single-node and multi-node testing, defines minimum required execution (run) times for each test. These requirements ensure that validation is conducted under appropriate conditions to accurately assess system stability, performance, and reliability.
+
+Successful completion of this checklist, with no errors or hardware faults observed in validation logs, confirms that the cluster has been properly configured, validated at both the single-node and multi-node levels, and is capable of supporting sustained AI workloads in a production environment.
 
 ### Prerequisites Validation
 
@@ -101,12 +103,29 @@ These checks ensure fundamental system health and proper GPU detection. For deta
 
 AGFHC (AMD GPU Field Health Check) provides structured recipes exercising PCIe, HBM, compute, power/thermal and fabric.
 
-| Recipe | Command | Purpose | Pass Criteria |
-|--------|---------|---------|---------------|
-| [all_lvl5](../common/system-validation.md#all_lvl5) | `/opt/amd/agfhc/agfhc -r all_lvl5 -o <output_dir>` | Broad ~2h system-level coverage (PCIe, HBM, compute, power) | Overall result PASS / return code 0 |
-| [hbm_lvl5](../common/system-validation.md#hbm_lvl5) (run twice) | `/opt/amd/agfhc/agfhc -r hbm_lvl5:i=2 -o <output_dir>` | Intensive HBM stress & ECC observation | Both iterations PASS / no memory errors |
-| [pcie_lvl2](../common/system-validation.md#pcie_lvl2) | `/opt/amd/agfhc/agfhc -r pcie_lvl2 -o <output_dir>` | PCIe bandwidth & link health | PASS / expected link stability |
-| [miniHPL](../common/system-validation.md#minihpl) (optional) | `/opt/amd/agfhc/agfhc -t miniHPL:d=120m -o <output_dir>` | Linpack-like integration stress (MI355X) | PASS / completes without failures |
+#### Single-Node Tests
+
+Following single-node tests must be performed at the required run time with no failures reported in validation logs.
+
+| Test | Command | Run Time | Purpose | Pass Criteria |
+|--------|---------|----------|---------|---------------|
+| [all_lvl5](../common/system-validation.md#all_lvl5) | `/opt/amd/agfhc/agfhc -r all_lvl5 -o <output_dir>` | 2 hours | Broad system-level coverage (PCIe, HBM, compute, power) | Overall result PASS / return code 0 |
+| [hbm_lvl5](../common/system-validation.md#hbm_lvl5) (4 iterations) | `/opt/amd/agfhc/agfhc -r hbm_lvl5:i=4 -o <output_dir>` | 8 hours | Intensive HBM stress & ECC observation | All iterations PASS / no memory errors |
+| [gfx_lvl4](../common/system-validation.md#gfx_lvl4) | `/opt/amd/agfhc/agfhc -r gfx_lvl4 -o <output_dir>` | 1 hour | GPU compute stress test | PASS / return code 0 |
+| [miniHPL](../common/system-validation.md#minihpl) | `/opt/amd/agfhc/agfhc -t minihpl:d=3h -o <output_dir>` | 3 hours (10 hours recommended) | Linpack-like integration stress | PASS / completes without failures |
+| [pcie_lvl2](../common/system-validation.md#pcie_lvl2) | `/opt/amd/agfhc/agfhc -r pcie_lvl2 -o <output_dir>` | 10 minutes | PCIe bandwidth & link health | PASS / expected link stability |
+| [Single-node RCCL](../common/rccl-benchmarking.md#single-node-rccl-testing) | `all_reduce_perf -b 8 -e 8G -f 2 -g 8` | 2–11 minutes | Single-node GPU interconnect validation | busbw meets expected thresholds |
+| [AI Workloads](../network/validation.md#ai-workload-validation-with-the-cluster-validation-suite) | See workload validation | 1–24 hours | Sustained AI workload (Llama 3.1 70B with JAX) | Completes without failures |
+
+#### Multi-Node Tests
+
+Following multi-node tests must be performed at the required run time with no failures reported in validation logs.
+
+| Test | Reference | Run Time | Purpose | Pass Criteria |
+|------|-----------|----------|---------|---------------|
+| [OFED Performance Tests](../network/rdma-benchmarking.md#ofed-performance-tests) | Network validation | 2 hours | RDMA fabric bandwidth and latency | All tests PASS / expected bandwidth |
+| [Multi-node RCCL](../network/validation.md#rccl-multi-node-fabric-test) | Network validation | Up to 128 nodes, 10 hours | Multi-node GPU fabric validation | All nodes PASS / expected bandwidth |
+| [AI Workloads](../network/validation.md#ai-workload-validation-with-the-cluster-validation-suite) | Cluster validation | 24 hours | Sustained AI workload (Llama 3.1 405B with JAX) | Completes without failures |
 
 Review `results.json` in the output directory or terminal summary; any FAIL requires remediation before acceptance.
 
diff --git a/docs/llms.txt b/docs/llms.txt
new file mode 100644
index 0000000..c6d01f7
--- /dev/null
+++ b/docs/llms.txt
@@ -0,0 +1,40 @@
+# AMD Instinct Customer Acceptance Guide
+
+> A structured, repeatable methodology for configuring, validating, benchmarking, and baselining AMD Instinct GPU platforms at both single-node and multi-node (cluster) levels. Covers node validation, cluster networking, RDMA benchmarking, and acceptance criteria for HPC and AI workloads.
+
+## GPU platforms
+
+- [AMD Instinct MI355X](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/gpus/mi355x.html): MI355X-specific prerequisites, health checks, validation steps, and performance acceptance criteria.
+- [AMD Instinct MI350X](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/gpus/mi350x.html): MI350X-specific prerequisites, health checks, validation steps, and performance acceptance criteria.
+- [AMD Instinct MI325X](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/gpus/mi325x.html): MI325X-specific requirements, specifications, and acceptance testing criteria.
+- [AMD Instinct MI300X](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/gpus/mi300x.html): MI300X-specific requirements, specifications, and acceptance testing criteria.
+
+## Node validation
+
+- [System prerequisites](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/prerequisites.html): System requirements common to all AMD Instinct GPU models.
+- [Firmware updates](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/firmware-updates.html): Supported methods for updating GPU runtime firmware and system firmware on AMD Instinct platforms.
+- [BIOS settings](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/bios-settings.html): BIOS configuration settings common to all AMD Instinct GPU models.
+- [Kernel parameters](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/kernel-parameters.html): GRUB and kernel parameter settings common to all AMD Instinct GPU models.
+- [OS tuning](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/os-tuning.html): C-states, NUMA configuration, and environment variables for AMD Instinct GPU systems.
+- [System setup](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/system-setup.html): Preparing, installing, and validating the ROCm software stack on AMD Instinct GPU systems.
+- [Health checks](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/health-checks.html): Basic system health checks to verify components are operating at peak performance before extensive validation.
+- [System validation](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/system-validation.html): RVS, AGFHC, and additional tools for validating AMD Instinct GPU systems.
+- [Workload validation](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/workload-validation.html): Validate AI model performance, including LLMs, on AMD Instinct systems.
+- [RCCL benchmarking](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/rccl-benchmarking.html): Benchmark and validate RCCL collective communication performance for single-node and multi-node configurations.
+
+## Cluster and network validation
+
+- [NIC driver installation](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/nic-installation.html): Vendor-specific guidance for installing and configuring NIC drivers and supporting software.
+- [Network configuration](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/configuration.html): Configure network routing to ensure each backend interface is used exclusively for GPU-driven cluster communications.
+- [Topology mapping](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/topology-mapping.html): Map GPUs and NICs by NUMA node and PCIe root complex to minimize latency for RDMA and AI/HPC workloads.
+- [Network optimization](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/optimization.html): NIC performance optimization for cluster networking.
+- [RDMA benchmarking](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/rdma-benchmarking.html): Validate RDMA performance and reliability, including link speed verification, RDMA benchmarks, and RCCL collective operations.
+- [Cluster validation](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/validation.html): Multi-node network and cluster validation for data throughput and cluster efficiency.
+
+## Reference
+
+- [Related documentation](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/reference/related-documentation.html): Reference documents and links for system setup and test execution.
+- [Glossary](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/reference/glossary.html): Terms and definitions used throughout this guide.
+- [ROCm technical support](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/reference/rocm-techsupport.html): Collect logs using the rocm_techsupport.sh utility for troubleshooting.
+
+---
diff --git a/docs/network/nic-installation.md b/docs/network/nic-installation.md
index b2040df..28e0491 100644
--- a/docs/network/nic-installation.md
+++ b/docs/network/nic-installation.md
@@ -64,10 +64,10 @@ Prerequisite: Driver & Tools version needs to match the firmware version.
 
    ```bash
    # Single card reset
-   nicctl reset card -c <card_uuid>
+   sudo nicctl reset card -c <card_uuid>
 
    # or reset all cards
-   nicctl reset card –all
+   sudo nicctl reset card –all
    ```
 
 Firmware and software updates are complete.
diff --git a/docs/network/optimization.md b/docs/network/optimization.md
deleted file mode 100644
index b54a0f1..0000000
--- a/docs/network/optimization.md
+++ /dev/null
@@ -1,93 +0,0 @@
-# Network Configuration for Performance Optimization
-
-Configure your NIC to ensure best performance. The following details the optimization based on a particular NIC.
-
-## AMD Pensando Pollara 400
-
-Several host configurations and NIC configurations should be done to achieve the best performance on the Pollara AI NIC.
-
-### Enable PFC
-
-The uplink port needs to be enabled for RX/TX pause and pause-type as PFC. The configuration can be applied to a single port by specifying the `<port_id>` or all the ports in the system:
-
-```bash
-# To get the port_id
-# nicctl show port
-# nicctl update port -p <port_id> --pause-type pfc --rx-pause enable --tx-pause enable
-```
-
-#### Recommended PFC Parameters
-
-Use the script below to update the DCQCN setting of Pollara AI NIC. The DSCP value or the Traffic Class value of your application, ex, TC value of perf-test and RCCL, should match the data_dscp value in the script.
-
-```bash
-#!/bin/bash
-for i in $(sudo nicctl show port | grep Port | awk {'print $3'}); do sudo nicctl update port -p $i --pause-type pfc --rx-pause enable --tx-pause enable; done
-for i in $(sudo nicctl show port | grep Port | awk {'print $3'}); do sudo nicctl update port --port $i --auto-neg enable; done
-cts_dscp=46
-cts_prio=6
-data_dscp=24
-data_prio=0
-default_prio=3
-cnp_dscp=46
-cnp_prio=6
-sudo nicctl update qos pfc --priority 0 --no-drop disable
-sudo nicctl update qos dscp-to-purpose --dscp $cts_dscp --purpose xccl-cts
-sudo nicctl update qos dscp-to-purpose $data_dscp --purpose data
-sudo nicctl update qos --classification-type pcp
-sudo nicctl update qos --classification-type dscp
-sudo nicctl update qos dscp-to-priority --dscp 0-63 --priority 0
-sudo nicctl update qos dscp-to-priority --dscp 0-23,25-45,47-63 --priority $default_prio
-sudo nicctl update qos dscp-to-priority --dscp $cts_dscp --priority strict
-sudo nicctl update qos dscp-to-priority --dscp $data_dscp --priority $data_prio
-sudo nicctl update qos dscp-to-priority --dscp $cnp_dscp --priority $cnp_prio
-sudo nicctl update qos pfc --priority $data_prio --no-drop enable
-sudo nicctl update qos scheduling --priority $data_prio,$default_prio,$cts_prio --dwrr 99,1,0 --rate-limit 0,0,10
-```
-
-### Configure DCQCN
-
-The DCQCN configuration is crucial to achieve the optimal performance in a bigger cluster. Use the following script to apply the DCQCN parameters that are recommended by AMD:
-
-```bash
-#!/bin/bash
-TOKEN_BUCKET_SIZE=800000
-AI_RATE=160
-ALPHA_UPDATE_INTERVAL=1
-ALPHA_UPDATE_G=512
-INITIAL_ALPHA_VALUE=64
-RATE_INCREASE_BYTE_COUNT=431068
-HAI_RATE=300
-RATE_REDUCE_MONITOR_PERIOD=1
-RATE_INCREASE_THRESHOLD=1
-RATE_INCREASE_INTERVAL=1
-CNP_DSCP=46
-ROCE_DEVICES=$(ibv_devices | grep ionic_ | awk '{print $1}' | paste -sd " ")
-for roce_dev in $ROCE_DEVICES
-do
-sudo nicctl update dcqcn -r $roce_dev -i 1 \
---token-bucket-size $TOKEN_BUCKET_SIZE \
---ai-rate $AI_RATE \
---alpha-update-interval $ALPHA_UPDATE_INTERVAL \
---alpha-update-g $ALPHA_UPDATE_G \
---initial-alpha-value $INITIAL_ALPHA_VALUE \
---rate-increase-byte-count $RATE_INCREASE_BYTE_COUNT \
---hai-rate $HAI_RATE \
---rate-reduce-monitor-period $RATE_REDUCE_MONITOR_PERIOD \
---rate-increase-threshold $RATE_INCREASE_THRESHOLD \
---rate-increase-interval $RATE_INCREASE_INTERVAL \
---cnp-dscp $CNP_DSCP
-done
-```
-
-## Broadcom 400G NIC
-
-For Broadcom 400G NICs, perform the following actions to guarantee proper operation and peak performance:
-
-* Enable PCIe relaxed ordering.
-* Enable RDMA support.
-* Select the RoCE performance profile.
-* Exclude all speeds except 400G from the speed mask.
-* Disable unused ports to optimize resources.
-
-For detailed configuration, use the scripts provided in the [cluster networking GitHub repository](https://github.com/ROCm/cluster-networking/tree/main/niccli_scripts)