wafer-cli 0.2.32__tar.gz → 0.2.34__tar.gz

wafer_cli-0.2.34/PKG-INFO

@@ -0,0 +1,260 @@
+Metadata-Version: 2.4
+Name: wafer-cli
+Version: 0.2.34
+Summary: CLI for running GPU workloads, managing remote workspaces, and evaluating/optimizing kernels
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: typer>=0.12.0
+Requires-Dist: trio>=0.24.0
+Requires-Dist: trio-asyncio>=0.15.0
+Requires-Dist: wafer-core>=0.1.0
+Requires-Dist: perfetto>=0.16.0
+Requires-Dist: posthog>=3.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: diff-cover>=8.0.0; extra == "dev"
+Requires-Dist: ruff>=0.4.0; extra == "dev"
+
+# Wafer CLI
+
+Run GPU workloads, optimize kernels, and query GPU documentation.
+
+## Getting Started
+
+```bash
+# Install
+cd apps/wafer-cli && uv sync
+
+# Use staging (workspaces and other features require staging)
+wafer config set api.environment staging
+
+# Login
+wafer login
+
+# Run a command on a remote GPU
+wafer remote-run -- nvidia-smi
+```
+
+## Commands
+
+### `wafer login` / `wafer logout` / `wafer whoami`
+
+Authenticate with GitHub OAuth.
+
+```bash
+wafer login          # Opens browser for GitHub OAuth
+wafer whoami         # Show current user
+wafer logout         # Remove credentials
+```
+
+### `wafer remote-run`
+
+Run any command on a remote GPU.
+
+```bash
+wafer remote-run -- nvidia-smi
+wafer remote-run --upload-dir ./my_code -- python3 train.py
+```
+
+### `wafer workspaces`
+
+Create and manage persistent GPU environments.
+
+**Available GPUs:**
+
+- `MI300X` - AMD Instinct MI300X (192GB HBM3, ROCm)
+- `B200` - NVIDIA Blackwell B200 (180GB HBM3e, CUDA) - default
+
+```bash
+wafer workspaces list
+wafer workspaces create my-workspace --gpu B200 --wait   # NVIDIA B200
+wafer workspaces create amd-dev --gpu MI300X             # AMD MI300X
+wafer workspaces ssh <workspace-id>
+wafer workspaces delete <workspace-id>
+```
+
+### `wafer agent`
+
+AI assistant for GPU kernel development. Helps with CUDA/Triton optimization, documentation queries, and performance analysis.
+
+```bash
+wafer agent "What is TMEM in CuTeDSL?"
+wafer agent -s "optimize this kernel" < kernel.py
+```
+
+### `wafer evaluate`
+
+Evaluate kernel correctness and performance against a reference implementation.
+
+**Functional format** (default):
+```bash
+# Generate template files
+wafer evaluate make-template ./my-kernel
+
+# Run evaluation
+wafer evaluate --impl kernel.py --reference ref.py --test-cases tests.json --benchmark
+```
+
+The implementation must define `custom_kernel(inputs)`, the reference must define `ref_kernel(inputs)` and `generate_input(**params)`.
+
+**KernelBench format** (ModelNew class):
+```bash
+# Extract a KernelBench problem as template
+wafer evaluate kernelbench make-template level1/1
+
+# Run evaluation
+wafer evaluate kernelbench --impl my_kernel.py --reference problem.py --benchmark
+```
+
+The implementation must define `class ModelNew(nn.Module)`, the reference must define `class Model`, `get_inputs()`, and `get_init_inputs()`.
+
+### `wafer wevin -t ask-docs`
+
+Query GPU documentation using the docs template.
+
+```bash
+wafer wevin -t ask-docs --json -s "What causes bank conflicts in shared memory?"
+```
+
+### `wafer corpus`
+
+Download documentation to local filesystem for agents to search.
+
+```bash
+wafer corpus list
+wafer corpus download cuda-programming-guide
+```
+
+---
+
+## Customization
+
+### `wafer remote-run` options
+
+```bash
+wafer remote-run --image pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel -- python3 script.py
+wafer remote-run --require-hwc -- ncu --set full python3 bench.py   # Hardware counters for NCU
+```
+
+### `wafer evaluate` options
+
+```bash
+wafer evaluate --impl k.py --reference r.py --test-cases t.json \
+    --target vultr-b200 \    # Specific GPU target
+    --benchmark \            # Measure performance
+    --profile                # Enable torch.profiler + NCU
+```
+
+### `wafer push` for multi-command workflows
+
+```bash
+WORKSPACE=$(wafer push ./project)
+wafer remote-run --workspace-id $WORKSPACE -- python3 test1.py
+wafer remote-run --workspace-id $WORKSPACE -- python3 test2.py
+```
+
+### Profile analysis
+
+```bash
+wafer nvidia ncu analyze profile.ncu-rep
+wafer nvidia nsys analyze profile.nsys-rep
+```
+
+---
+
+## Advanced
+
+### Local targets
+
+Bypass the API and SSH directly to your own GPUs:
+
+```bash
+wafer targets list
+wafer targets add ./my-gpu.toml
+wafer targets default my-gpu
+```
+
+### Defensive evaluation
+
+Detect evaluation hacking (stream injection, lazy evaluation, etc.):
+
+```bash
+wafer evaluate --impl k.py --reference r.py --test-cases t.json --benchmark --defensive
+```
+
+### Other tools
+
+```bash
+wafer perfetto <trace.json> --query "SELECT * FROM slice"   # Perfetto SQL queries
+wafer capture ./script.py                                    # Capture execution snapshot
+wafer compiler-analyze kernel.ptx                            # Analyze PTX/SASS
+```
+
+### ROCm profiling (AMD GPUs)
+
+```bash
+wafer rocprof-sdk ...
+wafer rocprof-systems ...
+wafer rocprof-compute ...
+```
+
+---
+
+## Shell Completion
+
+Enable tab completion for commands, options, and target names:
+
+```bash
+# Install completion (zsh/bash/fish)
+wafer --install-completion
+
+# Then restart your terminal, or source your shell config:
+source ~/.zshrc  # or ~/.bashrc
+```
+
+Now you can tab-complete:
+- Commands: `wafer eva<TAB>` → `wafer evaluate`
+- Options: `wafer evaluate --<TAB>`
+- Target names: `wafer evaluate --target v<TAB>` → `wafer evaluate --target vultr-b200`
+- File paths: `wafer evaluate --impl ./<TAB>`
+
+---
+
+## AI Assistant Skills
+
+Install the Wafer CLI skill to make wafer commands discoverable by your AI coding assistant:
+
+```bash
+# Install for all supported tools (Claude Code, Codex CLI, Cursor)
+wafer skill install
+
+# Install for a specific tool
+wafer skill install -t cursor    # Cursor
+wafer skill install -t claude    # Claude Code
+wafer skill install -t codex     # Codex CLI
+
+# Check installation status
+wafer skill status
+
+# Uninstall
+wafer skill uninstall
+```
+
+### Installing from GitHub (Cursor)
+
+You can also install the skill directly from GitHub in Cursor:
+
+1. Open Cursor Settings (Cmd+Shift+J / Ctrl+Shift+J)
+2. Navigate to **Rules** → **Add Rule** → **Remote Rule (Github)**
+3. Enter: `https://github.com/wafer-ai/skills`
+4. Cursor will automatically discover skills in `.cursor/skills/`
+
+The skill provides comprehensive guidance for GPU kernel development, including documentation lookup, trace analysis, kernel evaluation, and optimization workflows.
+
+---
+
+## Requirements
+
+- Python 3.10+
+- GitHub account (for authentication)

wafer_cli-0.2.34/README.md

@@ -0,0 +1,242 @@
+# Wafer CLI
+
+Run GPU workloads, optimize kernels, and query GPU documentation.
+
+## Getting Started
+
+```bash
+# Install
+cd apps/wafer-cli && uv sync
+
+# Use staging (workspaces and other features require staging)
+wafer config set api.environment staging
+
+# Login
+wafer login
+
+# Run a command on a remote GPU
+wafer remote-run -- nvidia-smi
+```
+
+## Commands
+
+### `wafer login` / `wafer logout` / `wafer whoami`
+
+Authenticate with GitHub OAuth.
+
+```bash
+wafer login          # Opens browser for GitHub OAuth
+wafer whoami         # Show current user
+wafer logout         # Remove credentials
+```
+
+### `wafer remote-run`
+
+Run any command on a remote GPU.
+
+```bash
+wafer remote-run -- nvidia-smi
+wafer remote-run --upload-dir ./my_code -- python3 train.py
+```
+
+### `wafer workspaces`
+
+Create and manage persistent GPU environments.
+
+**Available GPUs:**
+
+- `MI300X` - AMD Instinct MI300X (192GB HBM3, ROCm)
+- `B200` - NVIDIA Blackwell B200 (180GB HBM3e, CUDA) - default
+
+```bash
+wafer workspaces list
+wafer workspaces create my-workspace --gpu B200 --wait   # NVIDIA B200
+wafer workspaces create amd-dev --gpu MI300X             # AMD MI300X
+wafer workspaces ssh <workspace-id>
+wafer workspaces delete <workspace-id>
+```
+
+### `wafer agent`
+
+AI assistant for GPU kernel development. Helps with CUDA/Triton optimization, documentation queries, and performance analysis.
+
+```bash
+wafer agent "What is TMEM in CuTeDSL?"
+wafer agent -s "optimize this kernel" < kernel.py
+```
+
+### `wafer evaluate`
+
+Evaluate kernel correctness and performance against a reference implementation.
+
+**Functional format** (default):
+```bash
+# Generate template files
+wafer evaluate make-template ./my-kernel
+
+# Run evaluation
+wafer evaluate --impl kernel.py --reference ref.py --test-cases tests.json --benchmark
+```
+
+The implementation must define `custom_kernel(inputs)`, the reference must define `ref_kernel(inputs)` and `generate_input(**params)`.
+
+**KernelBench format** (ModelNew class):
+```bash
+# Extract a KernelBench problem as template
+wafer evaluate kernelbench make-template level1/1
+
+# Run evaluation
+wafer evaluate kernelbench --impl my_kernel.py --reference problem.py --benchmark
+```
+
+The implementation must define `class ModelNew(nn.Module)`, the reference must define `class Model`, `get_inputs()`, and `get_init_inputs()`.
+
+### `wafer wevin -t ask-docs`
+
+Query GPU documentation using the docs template.
+
+```bash
+wafer wevin -t ask-docs --json -s "What causes bank conflicts in shared memory?"
+```
+
+### `wafer corpus`
+
+Download documentation to local filesystem for agents to search.
+
+```bash
+wafer corpus list
+wafer corpus download cuda-programming-guide
+```
+
+---
+
+## Customization
+
+### `wafer remote-run` options
+
+```bash
+wafer remote-run --image pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel -- python3 script.py
+wafer remote-run --require-hwc -- ncu --set full python3 bench.py   # Hardware counters for NCU
+```
+
+### `wafer evaluate` options
+
+```bash
+wafer evaluate --impl k.py --reference r.py --test-cases t.json \
+    --target vultr-b200 \    # Specific GPU target
+    --benchmark \            # Measure performance
+    --profile                # Enable torch.profiler + NCU
+```
+
+### `wafer push` for multi-command workflows
+
+```bash
+WORKSPACE=$(wafer push ./project)
+wafer remote-run --workspace-id $WORKSPACE -- python3 test1.py
+wafer remote-run --workspace-id $WORKSPACE -- python3 test2.py
+```
+
+### Profile analysis
+
+```bash
+wafer nvidia ncu analyze profile.ncu-rep
+wafer nvidia nsys analyze profile.nsys-rep
+```
+
+---
+
+## Advanced
+
+### Local targets
+
+Bypass the API and SSH directly to your own GPUs:
+
+```bash
+wafer targets list
+wafer targets add ./my-gpu.toml
+wafer targets default my-gpu
+```
+
+### Defensive evaluation
+
+Detect evaluation hacking (stream injection, lazy evaluation, etc.):
+
+```bash
+wafer evaluate --impl k.py --reference r.py --test-cases t.json --benchmark --defensive
+```
+
+### Other tools
+
+```bash
+wafer perfetto <trace.json> --query "SELECT * FROM slice"   # Perfetto SQL queries
+wafer capture ./script.py                                    # Capture execution snapshot
+wafer compiler-analyze kernel.ptx                            # Analyze PTX/SASS
+```
+
+### ROCm profiling (AMD GPUs)
+
+```bash
+wafer rocprof-sdk ...
+wafer rocprof-systems ...
+wafer rocprof-compute ...
+```
+
+---
+
+## Shell Completion
+
+Enable tab completion for commands, options, and target names:
+
+```bash
+# Install completion (zsh/bash/fish)
+wafer --install-completion
+
+# Then restart your terminal, or source your shell config:
+source ~/.zshrc  # or ~/.bashrc
+```
+
+Now you can tab-complete:
+- Commands: `wafer eva<TAB>` → `wafer evaluate`
+- Options: `wafer evaluate --<TAB>`
+- Target names: `wafer evaluate --target v<TAB>` → `wafer evaluate --target vultr-b200`
+- File paths: `wafer evaluate --impl ./<TAB>`
+
+---
+
+## AI Assistant Skills
+
+Install the Wafer CLI skill to make wafer commands discoverable by your AI coding assistant:
+
+```bash
+# Install for all supported tools (Claude Code, Codex CLI, Cursor)
+wafer skill install
+
+# Install for a specific tool
+wafer skill install -t cursor    # Cursor
+wafer skill install -t claude    # Claude Code
+wafer skill install -t codex     # Codex CLI
+
+# Check installation status
+wafer skill status
+
+# Uninstall
+wafer skill uninstall
+```
+
+### Installing from GitHub (Cursor)
+
+You can also install the skill directly from GitHub in Cursor:
+
+1. Open Cursor Settings (Cmd+Shift+J / Ctrl+Shift+J)
+2. Navigate to **Rules** → **Add Rule** → **Remote Rule (Github)**
+3. Enter: `https://github.com/wafer-ai/skills`
+4. Cursor will automatically discover skills in `.cursor/skills/`
+
+The skill provides comprehensive guidance for GPU kernel development, including documentation lookup, trace analysis, kernel evaluation, and optimization workflows.
+
+---
+
+## Requirements
+
+- Python 3.10+
+- GitHub account (for authentication)

{wafer_cli-0.2.32 → wafer_cli-0.2.34}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "wafer-cli"
-version = "0.2.32"
+version = "0.2.34"
 description = "CLI for running GPU workloads, managing remote workspaces, and evaluating/optimizing kernels"
 readme = "README.md"
 requires-python = ">=3.11"

{wafer_cli-0.2.32 → wafer_cli-0.2.34}/tests/test_analytics.py

@@ -467,7 +467,7 @@ class TestLoginLogoutAnalytics:
              patch("wafer.analytics.track_login") as mock_track_login, \
              patch("wafer.analytics.init_analytics", return_value=True):
 
-            runner.invoke(app, ["auth", "login", "--token", "test-token"])
+            runner.invoke(app, ["login", "--token", "test-token"])
 
             # track_login should be called
             mock_track_login.assert_called_once_with("test-user-id", "test@example.com")
@@ -484,7 +484,7 @@ class TestLoginLogoutAnalytics:
              patch("wafer.analytics.track_logout") as mock_track_logout, \
              patch("wafer.analytics.init_analytics", return_value=True):
 
-            result = runner.invoke(app, ["auth", "logout"])
+            result = runner.invoke(app, ["logout"])
 
             assert result.exit_code == 0
             mock_track_logout.assert_called_once()

{wafer_cli-0.2.32 → wafer_cli-0.2.34}/tests/test_billing.py

@@ -210,7 +210,7 @@ class TestBillingUsageCommand:
                 )
                 mock_client.return_value.__enter__.return_value.get.return_value = mock_response
 
-                result = runner.invoke(app, ["config", "billing"])
+                result = runner.invoke(app, ["billing"])
 
                 assert result.exit_code != 0
                 assert "login" in result.output.lower()
@@ -242,7 +242,7 @@ class TestBillingUsageCommand:
                     mock_response.raise_for_status.return_value = None
                     mock_client.return_value.__enter__.return_value.get.return_value = mock_response
 
-                    result = runner.invoke(app, ["config", "billing", "--json"])
+                    result = runner.invoke(app, ["billing", "--json"])
 
                     assert result.exit_code == 0
                     data = json.loads(result.stdout)
@@ -275,7 +275,7 @@ class TestBillingUsageCommand:
                     mock_response.raise_for_status.return_value = None
                     mock_client.return_value.__enter__.return_value.get.return_value = mock_response
 
-                    result = runner.invoke(app, ["config", "billing"])
+                    result = runner.invoke(app, ["billing"])
 
                     assert result.exit_code == 0
                     assert "Pro" in result.output
@@ -294,7 +294,7 @@ class TestBillingUsageCommand:
                         httpx.RequestError("Connection failed")
                     )
 
-                    result = runner.invoke(app, ["config", "billing"])
+                    result = runner.invoke(app, ["billing"])
 
                     assert result.exit_code != 0
                     assert "error" in result.output.lower() or "reach" in result.output.lower()
@@ -317,7 +317,7 @@ class TestBillingTopupCommand:
                 )
                 mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
-                result = runner.invoke(app, ["config", "billing", "topup"])
+                result = runner.invoke(app, ["billing", "topup"])
 
                 assert result.exit_code != 0
                 assert "login" in result.output.lower()
@@ -343,7 +343,7 @@ class TestBillingTopupCommand:
                     mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
                     with patch("webbrowser.open") as mock_browser:
-                        result = runner.invoke(app, ["config", "billing", "topup"])
+                        result = runner.invoke(app, ["billing", "topup"])
 
                         assert result.exit_code == 0
                         # Verify $25 = 2500 cents was sent
@@ -372,7 +372,7 @@ class TestBillingTopupCommand:
                     mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
                     with patch("webbrowser.open") as mock_browser:
-                        result = runner.invoke(app, ["config", "billing", "topup", "100"])
+                        result = runner.invoke(app, ["billing", "topup", "100"])
 
                         assert result.exit_code == 0
                         call_args = mock_client.return_value.__enter__.return_value.post.call_args
@@ -381,14 +381,14 @@ class TestBillingTopupCommand:
 
     def test_amount_below_minimum(self) -> None:
         """Amount below $10 should error."""
-        result = runner.invoke(app, ["config", "billing", "topup", "5"])
+        result = runner.invoke(app, ["billing", "topup", "5"])
 
         assert result.exit_code != 0
         assert "10" in result.output  # Should mention minimum
 
     def test_amount_above_maximum(self) -> None:
         """Amount above $500 should error."""
-        result = runner.invoke(app, ["config", "billing", "topup", "600"])
+        result = runner.invoke(app, ["billing", "topup", "600"])
 
         assert result.exit_code != 0
         assert "500" in result.output  # Should mention maximum
@@ -410,7 +410,7 @@ class TestBillingTopupCommand:
                     )
                     mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
-                    result = runner.invoke(app, ["config", "billing", "topup"])
+                    result = runner.invoke(app, ["billing", "topup"])
 
                     assert result.exit_code != 0
                     assert "upgrade" in result.output.lower() or "portal" in result.output.lower()
@@ -436,7 +436,7 @@ class TestBillingTopupCommand:
                     mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
                     with patch("webbrowser.open") as mock_browser:
-                        result = runner.invoke(app, ["config", "billing", "topup", "--no-browser"])
+                        result = runner.invoke(app, ["billing", "topup", "--no-browser"])
 
                         assert result.exit_code == 0
                         assert "https://checkout.stripe.com/test" in result.output
@@ -460,7 +460,7 @@ class TestBillingPortalCommand:
                 )
                 mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
-                result = runner.invoke(app, ["config", "billing", "portal"])
+                result = runner.invoke(app, ["billing", "portal"])
 
                 assert result.exit_code != 0
                 assert "login" in result.output.lower()
@@ -483,7 +483,7 @@ class TestBillingPortalCommand:
                     mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
                     with patch("webbrowser.open") as mock_browser:
-                        result = runner.invoke(app, ["config", "billing", "portal"])
+                        result = runner.invoke(app, ["billing", "portal"])
 
                         assert result.exit_code == 0
                         mock_browser.assert_called_once_with("https://billing.stripe.com/test")
@@ -506,7 +506,7 @@ class TestBillingPortalCommand:
                     mock_client.return_value.__enter__.return_value.post.return_value = mock_response
 
                     with patch("webbrowser.open") as mock_browser:
-                        result = runner.invoke(app, ["config", "billing", "portal", "--no-browser"])
+                        result = runner.invoke(app, ["billing", "portal", "--no-browser"])
 
                         assert result.exit_code == 0
                         assert "https://billing.stripe.com/test" in result.output
@@ -528,4 +528,4 @@ class TestInsufficientCreditsError:
         message = _friendly_error(402, '{"detail": "Insufficient credits"}', "test-workspace")
 
         assert "credit" in message.lower()
-        assert "wafer config billing" in message.lower()
+        assert "wafer billing" in message.lower()