wafer-cli 0.2.32__py3-none-any.whl → 0.2.33__py3-none-any.whl

wafer/workspaces.py

@@ -39,13 +39,13 @@ def _friendly_error(status_code: int, response_text: str, workspace_id: str) ->
         User-friendly error message with suggested next steps
     """
     if status_code == 401:
-        return "Not authenticated. Run: wafer auth login"
+        return "Not authenticated. Run: wafer login"
 
     if status_code == 402:
         return (
             "Insufficient credits.\n"
-            "  Check usage: wafer config billing\n"
-            "  Add credits: wafer config billing topup"
+            "  Check usage: wafer billing\n"
+            "  Add credits: wafer billing topup"
         )
 
     if status_code == 404:
@@ -107,7 +107,7 @@ def _list_workspaces_raw() -> list[dict]:
             workspaces = response.json()
     except httpx.HTTPStatusError as e:
         if e.response.status_code == 401:
-            raise RuntimeError("Not authenticated. Run: wafer auth login") from e
+            raise RuntimeError("Not authenticated. Run: wafer login") from e
         raise RuntimeError(f"API error: {e.response.status_code} - {e.response.text}") from e
     except httpx.RequestError as e:
         raise RuntimeError(f"Could not reach API: {e}") from e
@@ -188,7 +188,7 @@ def list_workspaces(json_output: bool = False) -> str:
             workspaces = response.json()
     except httpx.HTTPStatusError as e:
         if e.response.status_code == 401:
-            raise RuntimeError("Not authenticated. Run: wafer auth login") from e
+            raise RuntimeError("Not authenticated. Run: wafer login") from e
         raise RuntimeError(f"API error: {e.response.status_code} - {e.response.text}") from e
     except httpx.RequestError as e:
         raise RuntimeError(f"Could not reach API: {e}") from e
@@ -307,7 +307,7 @@ def create_workspace(
             workspace = response.json()
     except httpx.HTTPStatusError as e:
         if e.response.status_code == 401:
-            raise RuntimeError("Not authenticated. Run: wafer auth login") from e
+            raise RuntimeError("Not authenticated. Run: wafer login") from e
         if e.response.status_code == 400:
             raise RuntimeError(f"Bad request: {e.response.text}") from e
         raise RuntimeError(f"API error: {e.response.status_code} - {e.response.text}") from e
@@ -413,7 +413,7 @@ def delete_workspace(workspace_id: str, json_output: bool = False) -> str:
             result = response.json()
     except httpx.HTTPStatusError as e:
         if e.response.status_code == 401:
-            raise RuntimeError("Not authenticated. Run: wafer auth login") from e
+            raise RuntimeError("Not authenticated. Run: wafer login") from e
         if e.response.status_code == 404:
             raise RuntimeError(f"Workspace not found: {workspace_id}") from e
         raise RuntimeError(f"API error: {e.response.status_code} - {e.response.text}") from e
@@ -691,7 +691,7 @@ def get_workspace_raw(workspace_id: str) -> dict:
             workspace = response.json()
     except httpx.HTTPStatusError as e:
         if e.response.status_code == 401:
-            raise RuntimeError("Not authenticated. Run: wafer auth login") from e
+            raise RuntimeError("Not authenticated. Run: wafer login") from e
         if e.response.status_code == 404:
             raise RuntimeError(f"Workspace not found: {workspace_id}") from e
         raise RuntimeError(f"API error: {e.response.status_code} - {e.response.text}") from e

wafer_cli-0.2.33.dist-info/METADATA

@@ -0,0 +1,260 @@
+Metadata-Version: 2.4
+Name: wafer-cli
+Version: 0.2.33
+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-0.2.32.dist-info → wafer_cli-0.2.33.dist-info}/RECORD

@@ -1,23 +1,23 @@
-wafer/GUIDE.md,sha256=aZMNTNHhSc5dmRskUnpgcGlHYgsbf5S6Q_Thn0xmN1A,3588
+wafer/GUIDE.md,sha256=G6P4aFZslEXiHmVjtTB3_OIpGK5d1tSiqxtawASVUZg,3588
 wafer/__init__.py,sha256=kBM_ONCpU6UUMBOH8Tmg4A88sNFnbaD59o61cJs-uYM,90
-wafer/agent_defaults.py,sha256=qpJvVyY7jw2EqQo_IZ4M4aR2-kKNomyTmoOOah1FW6I,1179
+wafer/agent_defaults.py,sha256=jJfTXqa9JO_fdVWi_G8_W3TXdYb7qPmK5IdmUCSLbgg,5761
 wafer/analytics.py,sha256=qLY6Z16usVHFD8TCv7XBuz7l47vXVdXk-qhOzA-hW_8,8179
 wafer/api_client.py,sha256=i_Az2b2llC3DSW8yOL-BKqa7LSKuxOr8hSN40s-oQXY,6313
 wafer/auth.py,sha256=dwss_se5P-FFc9IN38q4kh_dBrA6k-CguDBkivgcdj0,14003
 wafer/autotuner.py,sha256=41WYP41pTDvMijv2h42vm89bcHtDMJXObDlWmn6xpFU,44416
 wafer/baseline.py,sha256=OrGCAut_xtkH9Ogx4mMU5-94Q0oClIXqac94YRwqERY,21534
-wafer/billing.py,sha256=hEEwtrtIsbPQ3lLJNcyTLMsapUbcuvcVW_e9_0SxzVo,7199
-wafer/cli.py,sha256=jHh4EcCGheDq14E11rdSHXImMdriMSFb2vNcvhsV59A,273228
+wafer/billing.py,sha256=jbLB2lI4_9f2KD8uEFDi_ixLlowe5hasC0TIZJyIXRg,7163
+wafer/cli.py,sha256=DlsE-3cWZ-02yNb7fOf-9yXmQJyrSHsFWym2I3LpmrU,275688
 wafer/cli_instructions.py,sha256=bziUKDNDAXABVMvKPLEMXm-hFSD2TcFSh-FKRYa949k,4693
 wafer/config.py,sha256=h5Eo9_yfWqWGoPNdVQikI9GoZVUeysunSYiixf1mKcw,3411
-wafer/corpus.py,sha256=CY9T7wXENNDJxnrtI-XsQmXeptrFfKG4x-lngrc9_3s,24748
-wafer/evaluate.py,sha256=i15PliAVI3W04_4eju46PBDdh2BwSToLME5n7yGu7dU,187355
-wafer/global_config.py,sha256=iu1HbTDr1695tSeDG2NfkK7PiY7XD6vjCk37w1wHbgk,11920
+wafer/corpus.py,sha256=oQegXA43MuyRvYxOsWhmqeP5vMb5IKFHOvM-1RcahPA,22301
+wafer/evaluate.py,sha256=HMFQD-uwC6Wky1t_0JxYZaoHWgLaTBkjxOxgpZVnGrc,190519
+wafer/global_config.py,sha256=fhaR_RU3ufMksDmOohH1OLeQ0JT0SDW1hEip_zaP75k,11345
 wafer/gpu_run.py,sha256=TwqXy72T7f2I7e6n5WWod3xgxCPnDhU0BgLsB4CUoQY,9716
 wafer/inference.py,sha256=tZCO5i05FKY27ewis3CSBHFBeFbXY3xwj0DSjdoMY9s,4314
-wafer/kernel_scope.py,sha256=hKCwCIVZWl5xFdoA5G9kPucdG9O0jw9Zgyso-mc6aZo,20801
-wafer/ncu_analyze.py,sha256=f7yJayhmEjXn18g6MpxtQoN5_WW_kq4Qyxa1hd0tC74,24638
-wafer/nsys_analyze.py,sha256=4BV6vSTZy7jLzeAxdKJp6QceYy6t9SWGSnjDV8RqkcI,36129
+wafer/kernel_scope.py,sha256=YtnxknAChkJoeU_vIdxiqWsAITGBeabp9OGIK-X32i0,20796
+wafer/ncu_analyze.py,sha256=rAWzKQRZEY6E_CL3gAWUaW3uZ4kvQVZskVCPDpsFJuE,24633
+wafer/nsys_analyze.py,sha256=AhNcjPaapB0QCbqiHRXvyy-ccjevvVwEyxes84D28JU,36124
 wafer/nsys_profile.py,sha256=QFBl8pkr8r4uRNdNUO9gY-obj9slqpOgVYFZ_sXu6Nw,15478
 wafer/output.py,sha256=8jw5ifvIMK8ldyBMGW4NhrKvJPl66TV2Y2fJ5Tlhh1I,8293
 wafer/problems.py,sha256=ce2sy10A1nnNUG3VGsseTS8jL7LZsku4dE8zVf9JHQ4,11296
@@ -25,24 +25,26 @@ wafer/rocprof_compute.py,sha256=n_yOGZaFbOXna_ghhmYWXeyUoSabgH4KkjlYq38DlHo,1988
 wafer/rocprof_sdk.py,sha256=0Q7Ye6dUfa1anFZbqKc21rItgqva8V8VIZoSB7wqbmA,10085
 wafer/rocprof_systems.py,sha256=4IWbMcbYk1x_8iS7P3FC_u5sgH6EXADCtR2lV9id80M,18629
 wafer/specs_cli.py,sha256=frMEKwMflxVNpFlAuxprmr33ZZ1Oeh2lB0KWZ4oZWzw,4360
-wafer/ssh_keys.py,sha256=MxiHlSm6wuDUFzkOQtx5K7OIbx_a6bXxE-m8OpwLx98,8130
+wafer/ssh_keys.py,sha256=9kSdhV_dg9T6pQu2JmNQptarkkwGtN9rLyRkI1bW4i4,8094
 wafer/target_lock.py,sha256=SDKhNzv2N7gsphGflcNni9FE5YYuAMuEthngAJEo4Gs,7809
 wafer/targets.py,sha256=9r-iRWoKSH5cQl1LcamaX-T7cNVOg99ngIm_hlRk-qU,26922
 wafer/targets_cli.py,sha256=Oe3e02rSXeNrMbe_Qv9DNfQ8dEOKodtU7BbQQWxlNwA,16348
-wafer/targets_ops.py,sha256=wLPyq55H_wz0wEAEg8KFLYs9LIIyiVIphcsXD2NLa-E,22623
-wafer/trace_compare.py,sha256=COuxxKY874DteOSLUvJuJFREPMBSybq9dtANi3ATsg4,10803
+wafer/targets_ops.py,sha256=jN1oIBx0mutxRNE9xpIc7SaBxPkVmOyus2eqn0kEKNI,21475
+wafer/trace_compare.py,sha256=IBVSGI8u5A10haDzL4eQ0R24fM1G_dd1F3-4iEkG1EQ,6349
 wafer/tracelens.py,sha256=g9ZIeFyNojZn4uTd3skPqIrRiL7aMJOz_-GOd3aiyy4,7998
-wafer/wevin_cli.py,sha256=eo1ETsXIsCftXSG5AxEYYZipNGcXayKyIevs5F6MjXg,26140
-wafer/workspaces.py,sha256=J-TXGwHXSZlzRWCew63KNvk6HLJ-zTSELRgzjryTkMk,35710
-wafer/skills/wafer-guide/SKILL.md,sha256=UDsXCD5Kb-lDParKCTf2WkE3kodVs-rja8XeumSBO5U,3934
+wafer/wevin_cli.py,sha256=ruHROgLl4SL0UaKW9JbkTkVjtmtG3Jqigp7cnbQAbZ0,25564
+wafer/workspaces.py,sha256=k_iCZ-mOrG2KiTXqqcZ5_VifSIXsFGaZM4hjnxBnBmc,35666
+wafer/skills/wafer-guide/SKILL.md,sha256=KWetJw2TVTbz11_nzqazqOJWWRlbHRFShs4sOoreiWo,3255
 wafer/templates/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wafer/templates/aiter_optimize.py,sha256=IjUiwiDa4MBu_lsn0Fn2vc76Tx8kgA-i_SCsbm9kriA,2362
 wafer/templates/ask_docs.py,sha256=15t1Aa4WBMwMox8XmFdzyosOZfBLMdXyaxo3GDb7nTE,2254
-wafer/templates/optimize_kernel.py,sha256=Q4FA_8ECEegW_3DS51mkLCX6Vk1dcWWzY3A_RQ4NW8U,2576
-wafer/templates/optimize_kernelbench.py,sha256=T3co9Y9eSLWDrZG66gwQVFMdnGVoyUQos-TxnMMBLL8,3747
+wafer/templates/optimize_kernel.py,sha256=4-MaKm_C9BQHQEllrNLLYkcdhJpcj6D-8zbJ4FdLUEY,2444
+wafer/templates/optimize_kernelbench.py,sha256=aoOA13zWEl89r6QW03xF9NKxQ7j4mWe9rwua6-mlr4Y,4780
+wafer/templates/optimize_vllm.py,sha256=_D1rDP9wHA8CCvmoUrdLEW94MiaK4nAYJ-jbnpAvq7A,6154
 wafer/templates/trace_analyze.py,sha256=B7CiRlsokERzBjLL-k49kGjpU2zlJZqzTE05xbRS1WI,2878
 wafer/tests/test_eval_cli_parity.py,sha256=SGmaj2NGBZ7GdDF53bXsECvQbV21iHZw8YeL_MJOLk0,7206
-wafer_cli-0.2.32.dist-info/METADATA,sha256=snTvnaN37WG1rXCxW2YibK6CtBX9lhe8mOxEi9Th5iA,2799
-wafer_cli-0.2.32.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-wafer_cli-0.2.32.dist-info/entry_points.txt,sha256=WqB7hB__WhtPY8y1cO2sZiUz7fCq6Ik-usAigpeFvWE,41
-wafer_cli-0.2.32.dist-info/top_level.txt,sha256=2MK1IVMWfpLL8BZCQ3E9aG6L6L666gSA_teYlwan4fs,6
-wafer_cli-0.2.32.dist-info/RECORD,,
+wafer_cli-0.2.33.dist-info/METADATA,sha256=y3kmdBLh6-BZwFPcVmFYwOQQ3H1gM0ljANx1_W6FrEQ,6461
+wafer_cli-0.2.33.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+wafer_cli-0.2.33.dist-info/entry_points.txt,sha256=WqB7hB__WhtPY8y1cO2sZiUz7fCq6Ik-usAigpeFvWE,41
+wafer_cli-0.2.33.dist-info/top_level.txt,sha256=2MK1IVMWfpLL8BZCQ3E9aG6L6L666gSA_teYlwan4fs,6
+wafer_cli-0.2.33.dist-info/RECORD,,

wafer_cli-0.2.32.dist-info/METADATA

@@ -1,107 +0,0 @@
-Metadata-Version: 2.4
-Name: wafer-cli
-Version: 0.2.32
-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
-
-Wafer CLI gives coding agents direct access to GPU docs, trace analysis, and remote kernel evaluation.
-It helps you develop and optimize GPU kernels even when you are not working on a machine with a GPU.
-
-## Key features
-
-- Query GPU documentation with citations
-- Analyze GPU traces and profiles
-- Evaluate kernels on remote GPUs for correctness and performance
-- Run commands on GPU targets (remote or local)
-- Manage persistent workspaces
-
-## Quick start
-
-```bash
-uv tool install wafer-cli
-wafer login
-wafer remote-run -- nvidia-smi
-```
-
-## Common commands
-
-```bash
-wafer workspaces list
-wafer workspaces create my-workspace --wait
-wafer agent -t ask-docs --corpus cuda "What causes shared memory bank conflicts?"
-wafer agent -t trace-analyze --args trace=./profile.ncu-rep "Why is this kernel slow?"
-wafer evaluate --impl kernel.py --reference ref.py --test-cases tests.json --benchmark
-wafer nvidia ncu analyze profile.ncu-rep
-wafer corpus list
-```
-
-## Typical workflows
-
-### Query GPU documentation
-
-Download a documentation corpus and ask questions with citations.
-
-```bash
-wafer corpus download cuda
-wafer agent -t ask-docs --corpus cuda "What causes shared memory bank conflicts?"
-```
-
-### Analyze performance traces
-
-Use the trace analysis template or query trace data directly.
-
-```bash
-wafer agent -t trace-analyze --args trace=./profile.ncu-rep "Why is this kernel slow?"
-wafer nvidia perfetto query trace.json \
-  "SELECT name, dur/1e6 as ms FROM slice WHERE cat='kernel' ORDER BY dur DESC LIMIT 10"
-```
-
-### Evaluate kernels on remote GPUs
-
-Run correctness and performance checks on a remote target.
-
-```bash
-wafer evaluate \
-  --impl ./kernel.py \
-  --reference ./reference.py \
-  --test-cases ./tests.json \
-  --benchmark
-```
-
-### Run commands on a remote GPU
-
-```bash
-wafer remote-run -- nvidia-smi
-wafer remote-run --upload-dir ./my_code -- python3 train.py
-```
-
-### Manage workspaces
-
-```bash
-wafer workspaces list
-wafer workspaces create my-workspace --wait
-wafer workspaces ssh <workspace-id>
-wafer workspaces delete <workspace-id>
-```
-
-## Install the CLI skill (optional)
-
-```bash
-wafer skill install
-# or
-wafer skill install -t <claude/codex>
-```