alloc 0.4.0__tar.gz → 0.5.0__tar.gz

{alloc-0.4.0 → alloc-0.5.0}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: alloc
-Version: 0.4.0
+Version: 0.5.0
 Summary: Engineer-first training calibration: estimate VRAM fit, profile short runs, and pick GPU configs under real budget constraints.
 Author-email: Alloc Labs <hello@alloclabs.com>
-License: Apache-2.0
+License-Expression: Apache-2.0
 Project-URL: Homepage, https://alloclabs.com
 Project-URL: Repository, https://github.com/alloc-labs/alloc
 Classifier: Development Status :: 3 - Alpha
@@ -120,9 +120,29 @@ Wraps your command, monitors GPU memory/utilization/power via `pynvml`, and writ
 
 ```bash
 alloc login
-# Prompts for email + password, stores token in ~/.alloc/config.json
+# Prompts for email + password, stores token + refresh_token in ~/.alloc/config.json
+
+alloc login --token <ACCESS_TOKEN>
+# Paste an access token from the dashboard (no password prompt)
+```
+
+### `alloc whoami`: Show current auth + org context
+
+```bash
+alloc whoami
+alloc whoami --json
+```
+
+Prints the current identity (when logged in), plus objective, effective budget cap, and fleet counts.
+
+### `alloc logout`: Clear local session
+
+```bash
+alloc logout
 ```
 
+Clears saved `token`/`refresh_token` from `~/.alloc/config.json`.
+
 ### `alloc upload`: Upload artifact to dashboard
 
 ```bash
@@ -131,6 +151,8 @@ alloc upload alloc_artifact.json.gz
 
 Uploads a previously saved `.json.gz` artifact to the dashboard via `POST /runs/ingest`. Requires authentication (`alloc login` first).
 
+If your session token has expired and a `refresh_token` is available (password login flow), `alloc upload` refreshes once and retries automatically.
+
 ### `alloc catalog`: Browse GPU hardware catalog
 
 ```bash
@@ -148,6 +170,7 @@ Offline reference for GPU specs, interconnect details, and cloud pricing. Suppor
 ```bash
 alloc init                     # interactive wizard
 alloc init --yes               # non-interactive defaults (full catalog, 50/50 priority)
+alloc init --from-org --yes    # pull fleet/budget/objective from your org (requires alloc login)
 ```
 
 Creates a `.alloc.yaml` file in the current directory with your GPU fleet, explore list, budget, and priority weights. When present, `ghost`, `run`, and `scan` automatically use fleet context for recommendations. Use `--no-config` on any command to skip it.

{alloc-0.4.0 → alloc-0.5.0}/README.md

@@ -90,9 +90,29 @@ Wraps your command, monitors GPU memory/utilization/power via `pynvml`, and writ
 
 ```bash
 alloc login
-# Prompts for email + password, stores token in ~/.alloc/config.json
+# Prompts for email + password, stores token + refresh_token in ~/.alloc/config.json
+
+alloc login --token <ACCESS_TOKEN>
+# Paste an access token from the dashboard (no password prompt)
+```
+
+### `alloc whoami`: Show current auth + org context
+
+```bash
+alloc whoami
+alloc whoami --json
+```
+
+Prints the current identity (when logged in), plus objective, effective budget cap, and fleet counts.
+
+### `alloc logout`: Clear local session
+
+```bash
+alloc logout
 ```
 
+Clears saved `token`/`refresh_token` from `~/.alloc/config.json`.
+
 ### `alloc upload`: Upload artifact to dashboard
 
 ```bash
@@ -101,6 +121,8 @@ alloc upload alloc_artifact.json.gz
 
 Uploads a previously saved `.json.gz` artifact to the dashboard via `POST /runs/ingest`. Requires authentication (`alloc login` first).
 
+If your session token has expired and a `refresh_token` is available (password login flow), `alloc upload` refreshes once and retries automatically.
+
 ### `alloc catalog`: Browse GPU hardware catalog
 
 ```bash
@@ -118,6 +140,7 @@ Offline reference for GPU specs, interconnect details, and cloud pricing. Suppor
 ```bash
 alloc init                     # interactive wizard
 alloc init --yes               # non-interactive defaults (full catalog, 50/50 priority)
+alloc init --from-org --yes    # pull fleet/budget/objective from your org (requires alloc login)
 ```
 
 Creates a `.alloc.yaml` file in the current directory with your GPU fleet, explore list, budget, and priority weights. When present, `ghost`, `run`, and `scan` automatically use fleet context for recommendations. Use `--no-config` on any command to skip it.

{alloc-0.4.0 → alloc-0.5.0}/pyproject.toml

@@ -4,10 +4,10 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alloc"
-version = "0.4.0"
+version = "0.5.0"
 description = "Engineer-first training calibration: estimate VRAM fit, profile short runs, and pick GPU configs under real budget constraints."
 readme = "README.md"
-license = {text = "Apache-2.0"}
+license = "Apache-2.0"
 requires-python = ">=3.8"
 authors = [{name = "Alloc Labs", email = "hello@alloclabs.com"}]
 classifiers = [

{alloc-0.4.0 → alloc-0.5.0}/src/alloc/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-__version__ = "0.4.0"
+__version__ = "0.5.0"
 
 from alloc.ghost import ghost, GhostReport
 from alloc.callbacks import AllocCallback as HuggingFaceCallback

{alloc-0.4.0 → alloc-0.5.0}/src/alloc/callbacks.py

@@ -81,6 +81,42 @@ def _estimate_dataloader_wait(cv):
     return round((cv - 0.1) / 0.4 * 30.0, 1)
 
 
+def _detect_distributed():
+    # type: () -> tuple
+    """Detect if running inside a torch.distributed process group.
+
+    Returns (is_distributed, rank, world_size). Fail-safe: returns
+    (False, 0, 1) if torch.distributed is unavailable or not initialized.
+    """
+    try:
+        import torch.distributed as dist
+        if dist.is_initialized():
+            return True, dist.get_rank(), dist.get_world_size()
+    except Exception:
+        pass
+    return False, 0, 1
+
+
+def _estimate_comm_overhead(step_times_ms, dataloader_wait_pct=0.0):
+    # type: (List[float], float) -> Optional[float]
+    """Estimate communication overhead % for distributed training.
+
+    Uses the p90/p50 spread as a proxy for sync barrier delays.
+    Subtracts estimated dataloader contribution to avoid double-counting.
+    Returns None if insufficient data.
+    """
+    if len(step_times_ms) < 10:
+        return None
+    sorted_vals = sorted(step_times_ms)
+    p50 = _compute_percentile(sorted_vals, 50)
+    p90 = _compute_percentile(sorted_vals, 90)
+    if p50 <= 0:
+        return None
+    raw_pct = ((p90 - p50) / p50) * 100
+    comm_pct = max(0.0, raw_pct - dataloader_wait_pct)
+    return round(min(40.0, comm_pct), 1)
+
+
 def _write_callback_data(data):
     # type: (Dict[str, Any]) -> None
     """Write callback data to the alloc sidecar file.
@@ -101,6 +137,9 @@ def _build_sidecar(
     step_count,      # type: int
     step_times_ms,   # type: List[float]
     batch_size,      # type: Optional[int]
+    is_distributed=False,  # type: bool
+    rank=0,          # type: int
+    world_size=1,    # type: int
 ):
     # type: (...) -> Dict[str, Any]
     """Build the sidecar dict from collected timing data."""
@@ -124,6 +163,15 @@ def _build_sidecar(
         "batch_size": batch_size,
         "dataloader_wait_pct": dataloader_wait_pct,
     }
+
+    if is_distributed:
+        data["is_distributed"] = True
+        data["rank"] = rank
+        data["world_size"] = world_size
+        comm = _estimate_comm_overhead(step_times_ms, dataloader_wait_pct)
+        if comm is not None:
+            data["comm_overhead_pct"] = comm
+
     return data
 
 
@@ -142,9 +190,17 @@ try:
             self._step_start = None      # type: Optional[float]
             self._batch_size = None      # type: Optional[int]
             self._last_write_step = 0    # type: int
+            self._dist_checked = False   # type: bool
+            self._is_distributed = False  # type: bool
+            self._rank = 0               # type: int
+            self._world_size = 1         # type: int
 
         def on_step_begin(self, args, state, control, **kwargs):
             self._step_start = time.monotonic()
+            # Detect distributed once after process group is initialized
+            if not self._dist_checked:
+                self._is_distributed, self._rank, self._world_size = _detect_distributed()
+                self._dist_checked = True
 
         def on_step_end(self, args, state, control, **kwargs):
             self.step_count = state.global_step
@@ -183,6 +239,9 @@ try:
                 step_count=self.step_count,
                 step_times_ms=self._step_times_ms,
                 batch_size=self._batch_size,
+                is_distributed=self._is_distributed,
+                rank=self._rank,
+                world_size=self._world_size,
             )
             _write_callback_data(data)
 
@@ -214,9 +273,16 @@ try:
             self._step_start = None      # type: Optional[float]
             self._batch_size = None      # type: Optional[int]
             self._last_write_step = 0    # type: int
+            self._dist_checked = False   # type: bool
+            self._is_distributed = False  # type: bool
+            self._rank = 0               # type: int
+            self._world_size = 1         # type: int
 
         def on_train_batch_start(self, trainer, pl_module, batch, batch_idx):
             self._step_start = time.monotonic()
+            if not self._dist_checked:
+                self._is_distributed, self._rank, self._world_size = _detect_distributed()
+                self._dist_checked = True
 
         def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx):
             self.step_count = trainer.global_step
@@ -259,6 +325,9 @@ try:
                 step_count=self.step_count,
                 step_times_ms=self._step_times_ms,
                 batch_size=self._batch_size,
+                is_distributed=self._is_distributed,
+                rank=self._rank,
+                world_size=self._world_size,
             )
             _write_callback_data(data)
 

{alloc-0.4.0 → alloc-0.5.0}/src/alloc/catalog/__init__.py

@@ -76,6 +76,35 @@ def list_gpus() -> List[dict]:
     return sorted(result, key=lambda x: x["vram_gb"], reverse=True)
 
 
+def get_default_rate(gpu_name: str) -> Optional[float]:
+    """Look up the average default $/hr for a GPU by name or alias.
+
+    Tries to match the probe-reported GPU name against catalog display names.
+    Returns the average across clouds, or None if not found.
+    """
+    rate_card = _load_rate_card()
+    rates = rate_card.get("rates", {})
+
+    # Direct match by display name
+    for display_name, cloud_rates in rates.items():
+        if display_name.lower() in gpu_name.lower() or gpu_name.lower() in display_name.lower():
+            vals = [v for v in cloud_rates.values() if isinstance(v, (int, float))]
+            return sum(vals) / len(vals) if vals else None
+
+    # Try aliases → display name
+    for alias, stable_id in _ALIASES.items():
+        if alias.lower() in gpu_name.lower():
+            catalog = _load_catalog()
+            spec = catalog.get("gpus", {}).get(stable_id)
+            if spec:
+                dn = spec.get("display_name", "")
+                cloud_rates = rates.get(dn, {})
+                vals = [v for v in cloud_rates.values() if isinstance(v, (int, float))]
+                return sum(vals) / len(vals) if vals else None
+
+    return None
+
+
 def get_gpu(gpu_id: str) -> Optional[dict]:
     """Look up a GPU by stable ID or alias.