soup-cli 0.71.36__tar.gz → 0.71.37__tar.gz

{soup_cli-0.71.36 → soup_cli-0.71.37}/CHANGELOG.md

@@ -12,6 +12,45 @@ reproducing 70+ versions of notes.
 
 ## [Unreleased]
 
+## [0.71.37] - 2026-07-17
+
+**Every `pip install soup-cli[extra]` command now works on Windows `cmd.exe`**, and
+eval-gate benchmark tasks run instead of always failing.
+
+### Fixed
+
+- **Install hints are now quoted so they work in every shell.** Soup printed
+  `pip install 'soup-cli[ui]'` — bash / zsh / PowerShell syntax. `cmd.exe` has no
+  single-quote quoting, so it hands the quotes to pip verbatim and pip refuses:
+
+  ```
+  ERROR: Invalid requirement: "'soup-cli[train]'": Expected package name at the start of dependency specifier
+  ```
+
+  Every hint, README command, and docs example now uses `pip install
+  "soup-cli[extra]"`, which works in cmd, PowerShell, bash, and zsh alike — the
+  same spelling the repo already used for `pip install -e ".[dev]"`. Measured on
+  Windows: single quotes fail only on `cmd.exe`; double quotes pass everywhere;
+  dropping the quotes passes on Windows but breaks zsh, which globs the bracket.
+
+  Nothing in Soup can rescue the command after it is typed — pip and the shell
+  own it, and Soup is not installed yet when the README command runs — so the
+  fix is the spelling we print. A regression test now scans the package and every
+  docs code block for the single-quoted form.
+
+  If you followed an older tutorial and hit `Invalid requirement`, swap the `'`
+  for `"`; nothing is wrong with the package.
+
+- **Eval-gate `type: benchmark` tasks now actually run.** `eval/gate.py` probed
+  for a `forgetting.run_mini_benchmark` helper that never existed, so every
+  `type: benchmark` task in a gate suite failed 100% of the time — while
+  advising an `[eval]` extras install that could not fix it. The gate now calls
+  `ForgettingDetector` directly (the same way `soup ship` already did), and an
+  unknown benchmark name fails with the list of valid names. Thanks
+  [@Sanjays2402](https://github.com/Sanjays2402)!
+  ([#315](https://github.com/MakazhanAlpamys/Soup/pull/315), closes
+  [#310](https://github.com/MakazhanAlpamys/Soup/issues/310))
+
 ## [0.71.36] - 2026-07-16
 
 **Data Moat II** — a semantic layer over your training data, plus two tools for

{soup_cli-0.71.36 → soup_cli-0.71.37}/CONTRIBUTING.md

@@ -120,7 +120,7 @@ src/soup_cli/
   templates/          - 21 built-in soup.yaml templates (YAML + manifest.json) with load_template loader (v0.39.0, +bco v0.40.0, +4 compliance v0.71.35)
   ui/                 - Web UI (FastAPI + HTML/JS SPA)
 
-tests/                - Test suite (314 files, 16283 tests)
+tests/                - Test suite (315 files, 16288 tests)
 examples/             - Real-world config examples and datasets
 ```
 

{soup_cli-0.71.36 → soup_cli-0.71.37}/CONTRIBUTORS.md

@@ -52,6 +52,8 @@ Listed by first contribution. PR numbers link the work.
   - Honor configured vocab expansion in the ORPO / SimPO / GRPO trainers ([#295](https://github.com/MakazhanAlpamys/Soup/pull/295))
 - **Ekaanksh Patil** ([@Ekaanksh-dev](https://github.com/Ekaanksh-dev))
   - Batch the PRM reward forward pass in `PRMScorer.__call__` (single `[B, T]` forward) ([#301](https://github.com/MakazhanAlpamys/Soup/pull/301))
+- **Sanjay Santhanam** ([@Sanjays2402](https://github.com/Sanjays2402))
+  - Run built-in benchmark gate tasks through `ForgettingDetector` — every `type: benchmark` eval-gate task had always failed ([#315](https://github.com/MakazhanAlpamys/Soup/pull/315))
 
 ---
 

{soup_cli-0.71.36 → soup_cli-0.71.37}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: soup-cli
-Version: 0.71.36
+Version: 0.71.37
 Summary: Fine-tune and post-train LLMs in one command. No SSH, no config hell.
 Project-URL: Homepage, https://github.com/MakazhanAlpamys/Soup
 Project-URL: Repository, https://github.com/MakazhanAlpamys/Soup
@@ -176,7 +176,7 @@ Description-Content-Type: text/markdown
 Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
 
 ```bash
-pip install 'soup-cli[train]'   # add [train] to fine-tune; bare `soup-cli` is the light CLI
+pip install "soup-cli[train]"   # add [train] to fine-tune; bare `soup-cli` is the light CLI
 soup init --template chat
 soup train
 ```
@@ -212,7 +212,7 @@ infrastructure instead of improving models. Soup fixes that.
   separates them. The default is deliberately conservative; see the CHANGELOG.
 - **Two blocking bugs fixed:** the hardware-fit gate **refused to train any model you merged
   yourself** (a local checkpoint's name has no size marker, so it guessed 7B and predicted
-  16 GB), and every `pip install 'soup-cli[extra]'` hint printed **without the extra** —
+  16 GB), and every `pip install "soup-cli[extra]"` hint printed **without the extra** —
   17 sites where the suggested command succeeds and leaves the feature still broken.
 
 ```bash
@@ -248,11 +248,38 @@ Full history: [CHANGELOG.md](CHANGELOG.md) · [GitHub Releases](https://gi
 ### 1. Install
 
 ```bash
-pip install soup-cli            # light: CLI + config + data tools (no PyTorch)
-pip install 'soup-cli[train]'   # add the training stack (torch, transformers, peft, trl, …)
-pip install git+https://github.com/MakazhanAlpamys/Soup.git   # latest dev
+# Light core: CLI + config + data tools, no PyTorch
+pip install soup-cli
+
+# Add the training stack (torch, transformers, peft, trl, datasets, …)
+pip install "soup-cli[train]"
+
+# Everything (train + serve + ui + data) in one shot
+pip install "soup-cli[all]"
+
+# Or from GitHub (latest dev)
+pip install git+https://github.com/MakazhanAlpamys/Soup.git
 ```
 
+The full extras table (`fast`, `mlx`, `serve`, `eval`, `ui`, `vision`, `audio`, …) lives in
+[`docs/models.md`](docs/models.md#optional-extras).
+
+> **Use double quotes around the extra.** They are the only spelling that works in
+> every shell — `cmd.exe`, PowerShell, bash, and zsh.
+>
+> Older tutorials and videos (including some of ours) show the single-quoted
+> `pip install 'soup-cli[train]'`. That is bash / zsh / PowerShell syntax, and it
+> fails on Windows `cmd.exe`, which has no single-quote quoting and hands the
+> quotes straight to pip:
+>
+> ```
+> ERROR: Invalid requirement: "'soup-cli[train]'": Expected package name at the start of dependency specifier
+> ```
+>
+> If you hit that, swap the `'` for `"` — pip is rejecting a literal quote
+> character, nothing is wrong with the package. (Dropping the quotes entirely
+> works on Windows too, but zsh then reads `[train]` as a glob and fails.)
+
 `soup init`, `soup data …`, and the other data/inspection commands work on the light install.
 Fine-tuning (`soup train`) needs the `[train]` extra.
 
@@ -287,7 +314,7 @@ A complete `soup.yaml`:
 ```yaml
 base: meta-llama/Llama-3.1-8B-Instruct
 task: sft
-# backend: unsloth  # 2-5x faster, pip install 'soup-cli[fast]'
+# backend: unsloth  # 2-5x faster, pip install "soup-cli[fast]"
 
 data:
   train: ./data/train.jsonl

{soup_cli-0.71.36 → soup_cli-0.71.37}/README.md

@@ -32,7 +32,7 @@
 Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
 
 ```bash
-pip install 'soup-cli[train]'   # add [train] to fine-tune; bare `soup-cli` is the light CLI
+pip install "soup-cli[train]"   # add [train] to fine-tune; bare `soup-cli` is the light CLI
 soup init --template chat
 soup train
 ```
@@ -68,7 +68,7 @@ infrastructure instead of improving models. Soup fixes that.
   separates them. The default is deliberately conservative; see the CHANGELOG.
 - **Two blocking bugs fixed:** the hardware-fit gate **refused to train any model you merged
   yourself** (a local checkpoint's name has no size marker, so it guessed 7B and predicted
-  16 GB), and every `pip install 'soup-cli[extra]'` hint printed **without the extra** —
+  16 GB), and every `pip install "soup-cli[extra]"` hint printed **without the extra** —
   17 sites where the suggested command succeeds and leaves the feature still broken.
 
 ```bash
@@ -104,11 +104,38 @@ Full history: [CHANGELOG.md](CHANGELOG.md) · [GitHub Releases](https://gi
 ### 1. Install
 
 ```bash
-pip install soup-cli            # light: CLI + config + data tools (no PyTorch)
-pip install 'soup-cli[train]'   # add the training stack (torch, transformers, peft, trl, …)
-pip install git+https://github.com/MakazhanAlpamys/Soup.git   # latest dev
+# Light core: CLI + config + data tools, no PyTorch
+pip install soup-cli
+
+# Add the training stack (torch, transformers, peft, trl, datasets, …)
+pip install "soup-cli[train]"
+
+# Everything (train + serve + ui + data) in one shot
+pip install "soup-cli[all]"
+
+# Or from GitHub (latest dev)
+pip install git+https://github.com/MakazhanAlpamys/Soup.git
 ```
 
+The full extras table (`fast`, `mlx`, `serve`, `eval`, `ui`, `vision`, `audio`, …) lives in
+[`docs/models.md`](docs/models.md#optional-extras).
+
+> **Use double quotes around the extra.** They are the only spelling that works in
+> every shell — `cmd.exe`, PowerShell, bash, and zsh.
+>
+> Older tutorials and videos (including some of ours) show the single-quoted
+> `pip install 'soup-cli[train]'`. That is bash / zsh / PowerShell syntax, and it
+> fails on Windows `cmd.exe`, which has no single-quote quoting and hands the
+> quotes straight to pip:
+>
+> ```
+> ERROR: Invalid requirement: "'soup-cli[train]'": Expected package name at the start of dependency specifier
+> ```
+>
+> If you hit that, swap the `'` for `"` — pip is rejecting a literal quote
+> character, nothing is wrong with the package. (Dropping the quotes entirely
+> works on Windows too, but zsh then reads `[train]` as a glob and fails.)
+
 `soup init`, `soup data …`, and the other data/inspection commands work on the light install.
 Fine-tuning (`soup train`) needs the `[train]` extra.
 
@@ -143,7 +170,7 @@ A complete `soup.yaml`:
 ```yaml
 base: meta-llama/Llama-3.1-8B-Instruct
 task: sft
-# backend: unsloth  # 2-5x faster, pip install 'soup-cli[fast]'
+# backend: unsloth  # 2-5x faster, pip install "soup-cli[fast]"
 
 data:
   train: ./data/train.jsonl

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/backends-and-ops.md

@@ -79,7 +79,7 @@ Fine-tune on M1-M4 Macs via Apple's [MLX](https://github.com/ml-explore/mlx) fra
 
 ```bash
 # Install MLX support
-pip install 'soup-cli[mlx]'
+pip install "soup-cli[mlx]"
 ```
 
 ```yaml
@@ -108,7 +108,7 @@ Use the [Unsloth](https://github.com/unslothai/unsloth) backend for significantl
 
 ```bash
 # Install unsloth support
-pip install 'soup-cli[fast]'
+pip install "soup-cli[fast]"
 ```
 
 Then add one line to your config:
@@ -143,7 +143,7 @@ app from your `soup.yaml` for serverless, per-second-billed GPU training. The co
 base64-embedded as **data** — no code interpolation, no secrets in the generated stub.
 
 ```bash
-pip install 'soup-cli[modal]'   # only needed for live submit
+pip install "soup-cli[modal]"   # only needed for live submit
 
 # Plan-only (default): write the stub + print the `modal run` command.
 soup train --config soup.yaml --cloud modal --gpu a100
@@ -585,7 +585,7 @@ Full-screen Textual dashboard. Two-pane: run list (left) + selected-run detail
 (right). `r` refreshes, `q` quits.
 
 ```bash
-pip install 'soup-cli[tui]'
+pip install "soup-cli[tui]"
 soup tui --refresh 1.0 --limit 50
 ```
 

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/commands.md

@@ -255,9 +255,9 @@ soup adapters bisect <ckpt>... --eval-command "..."  Binary search over training
 soup lock write --base-sha <h> --dataset-sha <h> --env-hash <h>  Write soup.lock (v0.67.0)
 soup lock write --base-sha <h> --dataset-sha <h> --env-lock soup-env.lock  Auto-derive --env-hash from soup-env.lock (v0.71.1)
 soup lock show / soup lock check              Show + drift-check (exit 3 on drift)
-soup compile <program.py> --eval <suite> [--optimizer mipro|gepa|textgrad|copro|bootstrap_fewshot] [--plan-only]  DSPy / GEPA / TextGrad prompt-program compiler — live (v0.71.13; pip install 'soup-cli[compile]')
+soup compile <program.py> --eval <suite> [--optimizer mipro|gepa|textgrad|copro|bootstrap_fewshot] [--plan-only]  DSPy / GEPA / TextGrad prompt-program compiler — live (v0.71.13; pip install "soup-cli[compile]")
 soup distill-prompt --traces <jsonl> --teacher <m> --student <m> --strategy sft|preference|kl [--provider ollama|anthropic|vllm] [--base-url <url>] [--temperature F] [--max-rows N]  Distill prompt-heavy traces via a live teacher (v0.71.13)
-soup compile-tools <spec.json|yaml> --eval <jsonl> [--optimizer textgrad|gepa] [--plan-only]  TextGrad / GEPA tool-schema optimiser — live (v0.71.13; pip install 'soup-cli[compile]')
+soup compile-tools <spec.json|yaml> --eval <jsonl> [--optimizer textgrad|gepa] [--plan-only]  TextGrad / GEPA tool-schema optimiser — live (v0.71.13; pip install "soup-cli[compile]")
 soup apple-adapter <source-dir> --direction hf-to-mlx|mlx-to-hf|hf-to-apple|mlx-to-apple --output <dir> [--sign] [--plan-only]  PEFT LoRA <-> mlx-lm adapter conversion — live (v0.71.21; *-to-apple upstream-gated exit 3)
 soup local-rl init --db <path>                Create personal-LLM flywheel SQLite schema (v0.68.0)
 soup local-rl status --db <path>              Print interactions / thumbs-up / thumbs-down counters
@@ -299,7 +299,7 @@ server over **stdio**, so any MCP client — Claude Code, Cursor, Cline, Continu
 can drive Soup conversationally. Install the extra first:
 
 ```bash
-pip install 'soup-cli[mcp]'
+pip install "soup-cli[mcp]"
 ```
 
 Register it with your client. For **Claude Code** (`.mcp.json` in the repo) or

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/data.md

@@ -337,7 +337,7 @@ soup data generate --prompt "..." --validate
 # Auto-filter by quality (coherence scoring)
 soup data generate --prompt "..." --filter
 
-# Auto-dedup (MinHash, requires: pip install 'soup-cli[data]')
+# Auto-dedup (MinHash, requires: pip install "soup-cli[data]")
 soup data generate --prompt "..." --dedup
 
 # Full quality pipeline: validate + filter + dedup
@@ -591,7 +591,7 @@ soup data convert ./data/train.jsonl --to sharegpt --output converted.jsonl
 # Merge multiple datasets
 soup data merge data1.jsonl data2.jsonl --output merged.jsonl --shuffle
 
-# Remove near-duplicates (requires: pip install 'soup-cli[data]')
+# Remove near-duplicates (requires: pip install "soup-cli[data]")
 soup data dedup ./data/train.jsonl --threshold 0.8
 
 # Extended statistics (length distribution, token counts, languages)
@@ -814,7 +814,7 @@ Five checks: `length_bias` — the **#1 silent DPO degradation**: `chosen`
 systematically longer than `rejected`, reported as a Cohen's d effect size —
 `label_imbalance` (KTO desirable:undesirable ratio), `near_duplicates`
 (MinHash/LSH, reuses the `soup data dedup` kernel; requires
-`pip install 'soup-cli[data]'`, degrades to an advisory skip otherwise),
+`pip install "soup-cli[data]"`, degrades to an advisory skip otherwise),
 `identical_pairs` (`chosen == rejected` — zero preference signal), and
 `prompt_leak` (the prompt echoed verbatim inside the completion, a common
 synthetic-data pipeline bug). Same OK/MINOR/MAJOR taxonomy and exit codes as

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/evaluation.md

@@ -432,7 +432,7 @@ Full-featured evaluation platform with standard benchmarks, custom evals, LLM-as
 
 ```bash
 # Install eval dependencies
-pip install 'soup-cli[eval]'
+pip install "soup-cli[eval]"
 
 # Standard benchmarks (wraps lm-evaluation-harness)
 soup eval benchmark --model ./output --benchmarks mmlu,gsm8k,hellaswag

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/models.md

@@ -70,29 +70,29 @@ no PyTorch. Add `[train]` to fine-tune, or install other extras only when you ne
 
 | Extra | Install | What it adds |
 |---|---|---|
-| `train` | `pip install 'soup-cli[train]'` | Training stack: torch, transformers, peft, trl, datasets, bitsandbytes, accelerate |
-| `all` | `pip install 'soup-cli[all]'` | `train` + `serve` + `ui` + `data` in one shot |
-| `fast` | `pip install 'soup-cli[fast]'` | Unsloth backend (2-5x faster, lower VRAM) |
-| `vision` | `pip install 'soup-cli[vision]'` | Vision / multimodal fine-tuning (Pillow) |
-| `audio` | `pip install 'soup-cli[audio]'` | Audio / speech fine-tuning (librosa, soundfile) |
-| `mlx` | `pip install 'soup-cli[mlx]'` | Apple Silicon backend (mlx, mlx-lm) |
-| `qat` | `pip install 'soup-cli[qat]'` | Quantization-Aware Training (torchao) |
-| `serve` | `pip install 'soup-cli[serve]'` | Inference server (FastAPI + uvicorn) |
-| `serve-fast` | `pip install 'soup-cli[serve-fast]'` | vLLM inference backend (2-4x throughput) |
-| `sglang` | `pip install 'soup-cli[sglang]'` | SGLang inference backend |
-| `ui` | `pip install 'soup-cli[ui]'` | Web UI + inference server |
-| `tui` | `pip install 'soup-cli[tui]'` | Full-screen Textual dashboard (`soup tui`) |
-| `eval` | `pip install 'soup-cli[eval]'` | Benchmark evaluation (lm-evaluation-harness) |
-| `data` | `pip install 'soup-cli[data]'` | Deduplication (MinHash via datasketch) |
-| `data-pro` | `pip install 'soup-cli[data-pro]'` | Language detection + PII (langdetect, presidio) |
-| `deepspeed` | `pip install 'soup-cli[deepspeed]'` | Multi-GPU training (DeepSpeed ZeRO) |
-| `liger` | `pip install 'soup-cli[liger]'` | Liger Kernel fused ops |
-| `ring-attn` | `pip install 'soup-cli[ring-attn]'` | Ring FlashAttention (sequence parallelism) |
-| `onnx` / `tensorrt` | `pip install 'soup-cli[onnx]'` | ONNX / TensorRT-LLM export |
-| `awq` / `gptq` | `pip install 'soup-cli[awq]'` | AWQ / GPTQ quantized export |
-| `trackers` | `pip install 'soup-cli[trackers]'` | MLflow / SwanLab / Trackio logging |
-| `remote` | `pip install 'soup-cli[remote]'` | Remote datasets (s3 / gs / az / oci) |
-| `dev` | `pip install 'soup-cli[dev]'` | Tests + lint + types (pytest, ruff, mypy, pre-commit) |
+| `train` | `pip install "soup-cli[train]"` | Training stack: torch, transformers, peft, trl, datasets, bitsandbytes, accelerate |
+| `all` | `pip install "soup-cli[all]"` | `train` + `serve` + `ui` + `data` in one shot |
+| `fast` | `pip install "soup-cli[fast]"` | Unsloth backend (2-5x faster, lower VRAM) |
+| `vision` | `pip install "soup-cli[vision]"` | Vision / multimodal fine-tuning (Pillow) |
+| `audio` | `pip install "soup-cli[audio]"` | Audio / speech fine-tuning (librosa, soundfile) |
+| `mlx` | `pip install "soup-cli[mlx]"` | Apple Silicon backend (mlx, mlx-lm) |
+| `qat` | `pip install "soup-cli[qat]"` | Quantization-Aware Training (torchao) |
+| `serve` | `pip install "soup-cli[serve]"` | Inference server (FastAPI + uvicorn) |
+| `serve-fast` | `pip install "soup-cli[serve-fast]"` | vLLM inference backend (2-4x throughput) |
+| `sglang` | `pip install "soup-cli[sglang]"` | SGLang inference backend |
+| `ui` | `pip install "soup-cli[ui]"` | Web UI + inference server |
+| `tui` | `pip install "soup-cli[tui]"` | Full-screen Textual dashboard (`soup tui`) |
+| `eval` | `pip install "soup-cli[eval]"` | Benchmark evaluation (lm-evaluation-harness) |
+| `data` | `pip install "soup-cli[data]"` | Deduplication (MinHash via datasketch) |
+| `data-pro` | `pip install "soup-cli[data-pro]"` | Language detection + PII (langdetect, presidio) |
+| `deepspeed` | `pip install "soup-cli[deepspeed]"` | Multi-GPU training (DeepSpeed ZeRO) |
+| `liger` | `pip install "soup-cli[liger]"` | Liger Kernel fused ops |
+| `ring-attn` | `pip install "soup-cli[ring-attn]"` | Ring FlashAttention (sequence parallelism) |
+| `onnx` / `tensorrt` | `pip install "soup-cli[onnx]"` | ONNX / TensorRT-LLM export |
+| `awq` / `gptq` | `pip install "soup-cli[awq]"` | AWQ / GPTQ quantized export |
+| `trackers` | `pip install "soup-cli[trackers]"` | MLflow / SwanLab / Trackio logging |
+| `remote` | `pip install "soup-cli[remote]"` | Remote datasets (s3 / gs / az / oci) |
+| `dev` | `pip install "soup-cli[dev]"` | Tests + lint + types (pytest, ruff, mypy, pre-commit) |
 
 The complete, authoritative extras list is in [`pyproject.toml`](../pyproject.toml).
 

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/performance-and-quantization.md

@@ -36,7 +36,7 @@ Train with simulated quantization for significantly better post-quantization qua
 
 ```bash
 # Install QAT support
-pip install 'soup-cli[qat]'
+pip install "soup-cli[qat]"
 ```
 
 ```yaml
@@ -71,7 +71,7 @@ QAT works with all training tasks (SFT, DPO, GRPO, PPO, KTO, ORPO, SimPO, IPO, P
 For H100 / H200 / B100 / B200 GPUs, train with float8 matmuls for ~2x speedup vs bf16 at comparable quality. This extends QAT infrastructure via `torchao.float8`:
 
 ```bash
-pip install 'soup-cli[qat]'   # torchao >= 0.5.0 includes torchao.float8
+pip install "soup-cli[qat]"   # torchao >= 0.5.0 includes torchao.float8
 ```
 
 ```yaml
@@ -106,7 +106,7 @@ Bool `true` stays on the int8 QAT path for backward compatibility. FP8 requires
 Models with 128k+ vocabularies (Llama 3.1, Qwen2) materialise a huge `(batch, seq, vocab)` logits tensor that dominates VRAM. Cut Cross-Entropy computes the loss in chunks instead:
 
 ```bash
-pip install 'soup-cli[cce]'    # or: pip install cut-cross-entropy
+pip install "soup-cli[cce]"    # or: pip install cut-cross-entropy
 ```
 
 ```yaml
@@ -368,9 +368,9 @@ data:
 Install optional performance packages:
 
 ```bash
-pip install 'soup-cli[liger]'     # Liger Kernel fused operations
+pip install "soup-cli[liger]"     # Liger Kernel fused operations
 pip install flash-attn --no-build-isolation  # FlashAttention
-pip install 'soup-cli[ring-attn]' # Ring FlashAttention (sequence parallelism)
+pip install "soup-cli[ring-attn]" # Ring FlashAttention (sequence parallelism)
 ```
 
 

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/serving-and-export.md

@@ -97,7 +97,7 @@ Linux/macOS need only a C++ toolchain + CMake. CUDA llama.cpp builds are unteste
 Export models to ONNX format for use with [ONNX Runtime](https://onnxruntime.ai/):
 
 ```bash
-pip install 'soup-cli[onnx]'
+pip install "soup-cli[onnx]"
 soup export --model ./output --format onnx
 soup export --model ./output --format onnx --output ./model_onnx
 ```
@@ -107,7 +107,7 @@ soup export --model ./output --format onnx --output ./model_onnx
 Export models to TensorRT-LLM format for high-throughput GPU inference:
 
 ```bash
-pip install 'soup-cli[tensorrt]'
+pip install "soup-cli[tensorrt]"
 soup export --model ./output --format tensorrt
 soup export --model ./output --format tensorrt --output ./model_trt
 ```
@@ -212,7 +212,7 @@ Start a local OpenAI-compatible inference server:
 
 ```bash
 # Install server dependencies
-pip install 'soup-cli[serve]'
+pip install "soup-cli[serve]"
 
 # Start server
 soup serve --model ./output --port 8000
@@ -253,7 +253,7 @@ Use [vLLM](https://github.com/vllm-project/vllm) for significantly better throug
 
 ```bash
 # Install vLLM support
-pip install 'soup-cli[serve-fast]'
+pip install "soup-cli[serve-fast]"
 
 # Start with vLLM backend
 soup serve --model ./output --backend vllm
@@ -273,7 +273,7 @@ Use [SGLang](https://github.com/sgl-project/sglang) as an alternative high-throu
 
 ```bash
 # Install SGLang support
-pip install 'soup-cli[sglang]'
+pip install "soup-cli[sglang]"
 
 # Start with SGLang backend
 soup serve --model ./output --backend sglang
@@ -482,7 +482,7 @@ The OTLP endpoint is SSRF-hardened: only http/https schemes, plain HTTP only for
 Launch a local web interface to manage experiments, start training, explore data, and chat with models — all from your browser.
 
 ```bash
-pip install 'soup-cli[ui]'
+pip install "soup-cli[ui]"
 soup ui
 # -> opens http://127.0.0.1:7860 in your browser
 # -> prints auth token to console

{soup_cli-0.71.36 → soup_cli-0.71.37}/docs/training.md

@@ -531,7 +531,7 @@ Fine-tune vision-language models (LLaMA-3.2-Vision, Qwen2-VL, Pixtral) on image+
 
 ```bash
 # Install vision support
-pip install 'soup-cli[vision]'
+pip install "soup-cli[vision]"
 
 # Create a vision config
 soup init --template vision
@@ -581,7 +581,7 @@ Fine-tune audio-language models (Qwen2-Audio, Whisper) on audio+text data:
 
 ```bash
 # Install audio support
-pip install 'soup-cli[audio]'
+pip install "soup-cli[audio]"
 
 # Create an audio config
 soup init --template audio

{soup_cli-0.71.36 → soup_cli-0.71.37}/examples/README.md

@@ -137,7 +137,7 @@ soup train
 - Uses RoPE scaling (dynamic) to extend context to 128k tokens
 - Enables gradient checkpointing and FlashAttention for memory efficiency
 - Supports `linear`, `dynamic`, `yarn`, `longrope` scaling types
-- Optional Liger Kernel for fused ops: `pip install 'soup-cli[liger]'`
+- Optional Liger Kernel for fused ops: `pip install "soup-cli[liger]"`
 
 ### 9. Embedding Model Fine-Tuning
 
@@ -159,7 +159,7 @@ soup train
 Fine-tune audio-language models (Qwen2-Audio, Whisper):
 
 ```bash
-pip install 'soup-cli[audio]'
+pip install "soup-cli[audio]"
 soup init --template audio
 soup train
 ```
@@ -301,7 +301,7 @@ quantization: int8  # Reduces memory by 4x
 Unsloth is 2-5x faster training:
 
 ```bash
-pip install 'soup-cli[fast]'
+pip install "soup-cli[fast]"
 ```
 
 Then in your config:

{soup_cli-0.71.36 → soup_cli-0.71.37}/examples/configs/dpo_example.yaml

@@ -7,7 +7,7 @@
 
 base: meta-llama/Llama-3.1-8B-Instruct
 task: dpo
-# backend: unsloth  # 2-5x faster, pip install 'soup-cli[fast]'
+# backend: unsloth  # 2-5x faster, pip install "soup-cli[fast]"
 
 data:
   train: examples/data/dpo_sample.jsonl
@@ -32,7 +32,7 @@ training:
   # gradient_checkpointing: true  # Save memory on long sequences
   # packing: true                 # Pack short samples for faster training
   # use_flash_attn: true          # FlashAttention for faster attention
-  # use_liger: true               # Liger Kernel fused ops, pip install 'soup-cli[liger]'
+  # use_liger: true               # Liger Kernel fused ops, pip install "soup-cli[liger]"
   lora:
     r: 16
     alpha: 32

{soup_cli-0.71.36 → soup_cli-0.71.37}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "soup-cli"
-version = "0.71.36"
+version = "0.71.37"
 description = "Fine-tune and post-train LLMs in one command. No SSH, no config hell."
 readme = "README.md"
 license = "Apache-2.0"

{soup_cli-0.71.36 → soup_cli-0.71.37}/src/soup_cli/__init__.py

@@ -1,3 +1,3 @@
 """Soup CLI — Fine-tune and post-train LLMs in one command."""
 
-__version__ = "0.71.36"
+__version__ = "0.71.37"

{soup_cli-0.71.36 → soup_cli-0.71.37}/src/soup_cli/cloud/modal.py

@@ -280,7 +280,7 @@ def submit_modal_run(plan: CloudPlan, *, env: Optional[Mapping] = None) -> int:
         import modal  # noqa: F401 — presence check only
     except ImportError as exc:
         raise RuntimeError(
-            "Modal SDK not installed. Run `pip install 'soup-cli[modal]'`."
+            "Modal SDK not installed. Run `pip install \"soup-cli[modal]\"`."
         ) from exc
     import subprocess
 

{soup_cli-0.71.36 → soup_cli-0.71.37}/src/soup_cli/commands/compile_cmd.py

@@ -2,7 +2,7 @@
 
 Renders a ``CompilePlan`` panel and, when ``--plan-only`` is omitted, runs
 the live optimizer (v0.71.13 #225). A missing optimizer library surfaces a
-friendly exit-2 advisory naming ``pip install 'soup-cli[compile]'``.
+friendly exit-2 advisory naming ``pip install "soup-cli[compile]"``.
 """
 
 from __future__ import annotations

{soup_cli-0.71.36 → soup_cli-0.71.37}/src/soup_cli/commands/data.py

@@ -264,9 +264,11 @@ def _semantic_dedup(
         console.print(
             "[red]Semantic dedup needs PyTorch + transformers.[/]\n"
             # \[train] is escaped: Rich would otherwise eat the bracket as a
-            # markup tag and print `pip install 'soup-cli'` -- a command that
+            # markup tag and print `pip install "soup-cli"` -- a command that
             # installs the package WITHOUT the extra the user is missing.
-            "Install with: [bold]pip install 'soup-cli\\[train]'[/]"
+            # Double quotes, not single: cmd.exe cannot strip `'` and pip then
+            # rejects the requirement outright.
+            "Install with: [bold]pip install \"soup-cli\\[train]\"[/]"
         )
         raise typer.Exit(1)
     except (ValueError, TypeError) as exc:
@@ -358,7 +360,7 @@ def dedup(
     except ImportError:
         console.print(
             "[red]datasketch not installed.[/]\n"
-            "Install with: [bold]pip install 'soup-cli\\[data]'[/]"
+            "Install with: [bold]pip install \"soup-cli\\[data]\"[/]"
         )
         raise typer.Exit(1)
 

{soup_cli-0.71.36 → soup_cli-0.71.37}/src/soup_cli/commands/data_canary.py

@@ -191,7 +191,7 @@ def check(
             "[red]soup data canary check needs PyTorch + transformers.[/]\n"
             # \[train] escaped: Rich would eat the bracket and print a
             # command that installs WITHOUT the extra.
-            "Install with: [bold]pip install 'soup-cli\\[train]'[/]"
+            "Install with: [bold]pip install \"soup-cli\\[train]\"[/]"
         )
         raise typer.Exit(1)
     except (ValueError, OSError, RuntimeError) as exc:

{soup_cli-0.71.36 → soup_cli-0.71.37}/src/soup_cli/commands/data_topics.py

@@ -117,7 +117,7 @@ def topics(
             "[red]soup data topics needs PyTorch + transformers.[/]\n"
             # \[train] escaped: Rich would eat the bracket and print a
             # command that installs WITHOUT the extra.
-            "Install with: [bold]pip install 'soup-cli\\[train]'[/]"
+            "Install with: [bold]pip install \"soup-cli\\[train]\"[/]"
         )
         raise typer.Exit(1)
     except (ValueError, TypeError) as exc:

{soup_cli-0.71.36 → soup_cli-0.71.37}/src/soup_cli/commands/eval.py

@@ -108,7 +108,7 @@ def benchmark(
     except ImportError:
         console.print(
             "[red]lm-eval not installed.[/]\n"
-            "Install with: [bold]pip install 'soup-cli\\[eval]'[/]"
+            "Install with: [bold]pip install \"soup-cli\\[eval]\"[/]"
         )
         raise typer.Exit(1)