tuieval 0.2.0.dev1__py3-none-any.whl → 0.2.0.dev2__py3-none-any.whl

tuieval/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.2.0.dev1'
-__version_tuple__ = version_tuple = (0, 2, 0, 'dev1')
+__version__ = version = '0.2.0.dev2'
+__version_tuple__ = version_tuple = (0, 2, 0, 'dev2')
 
 __commit_id__ = commit_id = None

tuieval/compare.py

@@ -3,7 +3,7 @@
 Usage:
     tuieval compare                          # everything in results/<model>/<pack>.json
     tuieval compare --speed                  # speed & tokens table (TTFT, tok/s, tokens, memory)
-    tuieval compare --machine m4pro-24gb     # speed on another machine (measured there, or projected)
+    tuieval compare --machine m3max-64gb     # speed on another machine (measured there, or projected)
     tuieval compare --pairwise --failures    # is each difference real? which tests failed?
     tuieval compare results/some-model/*.json    # specific files
 """

tuieval/export.py

@@ -1,17 +1,18 @@
 """Export a model's serving settings to the pi coding agent, so pi serves it exactly as the evals did:
 the same model file, output-affecting flags and context, plus the speed flags tuned on this machine.
 
-  a section in llama-router's presets (~/models/presets.ini; keys that equal the [*] section are
-  left out) and an entry under pi's `llama` provider modelOverrides. Models on llama servers only.
+  a section in a llama.cpp router's model presets file (llama-server --models-preset; keys that
+  equal its [*] section are left out) and an entry under pi's `llama` provider modelOverrides.
+  Models on llama servers only.
 
 Every file is backed up next to itself (<file>.bak-tuieval-<time>) before it changes, and the diff
 is shown first. Paths come from models.toml [export.pi]:
 
   [export.pi]
-  presets = "~/models/presets.ini"            # llama-router --models-preset
+  presets = "/path/to/presets.ini"            # required: the router's --models-preset file
   pi_models = "~/.pi/agent/models.json"
   llama_provider = "llama"                     # pi's provider name for the router
-  servers = ["llama"]                          # models.toml servers that llama-router can serve
+  servers = ["llama"]                          # models.toml servers the router can serve
 """
 import configparser
 import difflib
@@ -23,7 +24,7 @@ import time
 
 from . import engine as engine_mod
 
-DEFAULTS = {"presets": "~/models/presets.ini", "pi_models": "~/.pi/agent/models.json",
+DEFAULTS = {"presets": None, "pi_models": "~/.pi/agent/models.json",
             "llama_provider": "llama", "servers": ["llama"]}
 # llama.cpp short flags -> the long names presets use as keys
 SHORT = {"-m": "model", "-c": "ctx-size", "-t": "threads", "-tb": "threads-batch", "-ub": "ubatch-size",
@@ -127,7 +128,7 @@ def plan(eng, label, model_id=None, name=None):
     m = eng.model(label)
     s = settings(eng)
     if m["server"] not in s["servers"]:
-        raise ExportError(f"{label} runs on the {m['server']} server; pi export writes llama-router presets, "
+        raise ExportError(f"{label} runs on the {m['server']} server; pi export writes llama.cpp router presets, "
                           "for llama servers ([export.pi] servers lists them)")
     model_id = model_id or m.get("pi_id") or default_id(m)
     name = name or m.get("pi_name") or model_id
@@ -157,6 +158,8 @@ def plan(eng, label, model_id=None, name=None):
     for k, key in SAMPLING_KEYS.items():
         if sampling.get(k) is not None:
             flags[key] = str(sampling[k])
+    if not s.get("presets"):
+        raise ExportError("set [export.pi] presets in models.toml to your llama.cpp router's --models-preset file")
     path = engine_mod.expand(s["presets"])
     old = _read(path)
     if not old:
@@ -183,7 +186,7 @@ def plan(eng, label, model_id=None, name=None):
                   "maxTokens": entry.get("maxTokens", sampling.get("max_tokens")),
                   "reasoning": bool(sampling.get("enable_thinking", True)),
                   "input": ["text", "image"] if vision else ["text"]})
-    notes.append("restart llama-router to load the new presets (llama-router restart)")
+    notes.append("restart the llama.cpp router so it reads the new presets")
     if sampling.get("reasoning_effort"):
         notes.append(f"the evals ran reasoning_effort {sampling['reasoning_effort']}: pick that thinking level in pi")
     pi_new = json.dumps(pi, indent=2, ensure_ascii=False) + "\n"

tuieval/machines.py

@@ -1,6 +1,6 @@
 """Which machine this is, what a model needs, and whether it fits.
 
-    detect()              -> Machine (chip, cores, RAM, GPU memory limit, id like "m1max-32gb")
+    detect()              -> Machine (chip, cores, RAM, GPU memory limit, id like "m3max-64gb")
     read_gguf(path)       -> GGUF header facts (architecture, layers, KV heads, context length, …)
     fit(model_path, …)    -> Fit (largest context that fits this machine, estimated memory)
 
@@ -219,8 +219,7 @@ def swapped_out_bytes():
 
 
 # ---------------------------------------------------------------- GPU residency
-# Measured on an M1 Max 32 GB with macOS 27.0: once the system's GPU allocations exceed about half
-# of RAM, the GPU driver evicts and re-maps memory on every command submission (70-95% of the
+# On Apple Silicon Macs, once the system's GPU allocations exceed about half of RAM, the GPU driver evicts and re-maps memory on every command submission (70-95% of the
 # server's CPU in the kernel, GPU idle), whatever iogpu.wired_limit_mb says. Servers that submit
 # many small GPU jobs collapse; see the stall guard in docs/models.md.
 RESIDENCY_FRACTION = 0.5

tuieval/run_evals.py

@@ -576,7 +576,7 @@ def cmd_export(argv):
                                 description="Write a model's serving settings (model file, output-affecting flags, "
                                             "context and the speed flags tuned on this machine) to another tool. "
                                             "Shows the diff and asks first; every file is backed up.")
-    p.add_argument("target", choices=["pi"], help="pi: the pi coding agent (llama-router presets and pi's "
+    p.add_argument("target", choices=["pi"], help="pi: the pi coding agent (llama.cpp router presets and pi's "
                                                   "models.json)")
     p.add_argument("labels", nargs="+", help="models to export")
     p.add_argument("--id", help="the model id pi sees (default: models.toml pi_id, else the GGUF's name)")

tuieval/templates/models.toml

@@ -107,7 +107,7 @@ headers = { "X-Title" = "tuieval" }
 # cmd = ["~/llama.cpp/build/bin/llama-bench"]
 
 # Optional per-machine settings, by machine id (tuieval machines shows the ids).
-# [machines.m4pro-24gb]
+# [machines.m3max-64gb]
 # memory_headroom_gb = 3       # GPU memory kept free for macOS and other apps (default 4)
 # gpu_residency_gb = 12        # GPU memory the driver keeps resident before churning (default: half of RAM)
 

{tuieval-0.2.0.dev1.dist-info → tuieval-0.2.0.dev2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: tuieval
-Version: 0.2.0.dev1
+Version: 0.2.0.dev2
 Summary: Evaluate local and frontier LLMs on your own questions: accuracy, speed, tokens and PASS/FAIL verdicts, in the terminal.
 Project-URL: Homepage, https://github.com/ashe-wb/tuieval
 Project-URL: Issues, https://github.com/ashe-wb/tuieval/issues
@@ -47,7 +47,7 @@ tuieval                        # open the TUI
 
 Once you've added your own packs and models, the setup screen looks like this (packs on the left, models with a verdict code per use case on the right, the highlighted model's details below):
 
-![tuieval's setup screen with five eval packs and a dozen local models](https://raw.githubusercontent.com/ashe-wb/tuieval/main/docs/images/tui-setup.png)
+![tuieval's setup screen with five eval packs and three models with their verdicts](https://raw.githubusercontent.com/ashe-wb/tuieval/main/docs/images/tui-setup.png)
 
 ## What you get
 

{tuieval-0.2.0.dev1.dist-info → tuieval-0.2.0.dev2.dist-info}/RECORD

@@ -1,16 +1,16 @@
 tuieval/__init__.py,sha256=myVXVX7htbwezW6k3x_FuKgn1RSZ2WcTaDEMByGn6Wg,312
 tuieval/__main__.py,sha256=E6Gls0DNz8GQK2K-kOUIx8cYhgANW_CH54VKrfCfs14,52
-tuieval/_version.py,sha256=Ru8zPUF025lmmQMlqsMXHYb46DrBOclru6QeHHNHADg,533
+tuieval/_version.py,sha256=EOZVyFNK9VEmUe6471HI7YHfwqJ5uDi2cXJHVylN6eI,533
 tuieval/cli.py,sha256=ZaLoWrxyCABu4SJzx5U2gVUUmwcwRgpZVqdqnxyFMOk,4167
 tuieval/client.py,sha256=Vui7ucVv_GiKObGoVS_EWSZFUKPou9PWmutqMTrahXk,9313
-tuieval/compare.py,sha256=MMbWEBYN6OrVyhaoAAbhJ_MDH7WnC7CYKrP_89kwbS8,25460
+tuieval/compare.py,sha256=b-rVcMwq0Tos3oNKcpUP1HXULKhAQNAS4rlXYSY7t6k,25460
 tuieval/engine.py,sha256=Amft1EL0iQVsiutfN7vQpwRXMCq_TYryDj0pMtY2suM,94195
-tuieval/export.py,sha256=hc4-TUvO4vTFL1oAaOKa818-Te0d4d-CzxmQAmXQsYI,9502
-tuieval/machines.py,sha256=zTB7yejILBnMMG5GI9hID4VIpeD3EOEHjjA71zn7pFs,12998
+tuieval/export.py,sha256=dbHQgL_ubWtIPM1sLzAew_gETnrDJyd0zgqVA5vkpXM,9657
+tuieval/machines.py,sha256=CeestY-_6h8ZKhJbBA_xyf0prqBvjvdgs2XJtCJYnNg,12974
 tuieval/packs.py,sha256=Go-kTSPvYZriXMo4DvmqNNL-iD0J92MKLiNCnP2chJ8,10305
 tuieval/profiles.py,sha256=soeLxjdB-l-OxSY8jZ4yjwfdSnsBV-QICcwKxRJS7nQ,3663
 tuieval/remove.py,sha256=Vwh43nm9lVb9U9aN-h6CMYbkTwdR3UWfZObwweF72n0,5157
-tuieval/run_evals.py,sha256=k-0Qck1-FzLPzGX4Ll3O3IdNzADpEsiCa6cLPeSx8jE,37522
+tuieval/run_evals.py,sha256=uPzidbRPUduBwP8sKyzg-U8cka0p-RsbZlVis6qQTlk,37526
 tuieval/scaffold.py,sha256=-AE5vKXeTtMZJ8OMk4UiIstoUWozTKjThKxZ87j0f9E,4720
 tuieval/selftest.py,sha256=xKfR73wMTYcDRSCBYQTNyKeR9bYU5HIYUSg7oZvNCyI,9330
 tuieval/tui.py,sha256=8diKtYE31ZUKq62rfMGdMkEbHgK6arRYpjFu-wcMVZs,131997
@@ -25,7 +25,7 @@ tuieval/graders/code.py,sha256=mNoPw-C_lNaXTTU57TJjhcVPTvdR400PxoE9Ow-tgHg,3703
 tuieval/graders/rag.py,sha256=j_gEjmaXmY_hgKu7-7pVQpQ8Cwb49gadnwFurih-1Hw,1447
 tuieval/graders/reply.py,sha256=BdkL7EWSSMoyjwCOFa97TTQMR1QyrpMH-ntcgjzDPEg,2199
 tuieval/graders/tool_call.py,sha256=_QXURtOk4ZKBnxXVMzFL1c9jWLWksRlLZ4VqOCL0t90,3578
-tuieval/templates/models.toml,sha256=8Lwcni1eWyc7sAFUIr90aOSi_YSyMnW9TzvTtKX7T-M,7879
+tuieval/templates/models.toml,sha256=bZRpQgj2LFeEQhnqkf0YUhrGybrugCilyWTg19_W4g4,7879
 tuieval/templates/packs/answer/pack.toml,sha256=8bjMBxG1Zz3yxEnYCqRTNBJ-JGYlquqiK19p8URWwTc,1167
 tuieval/templates/packs/answer/system.txt,sha256=m4V6X1i49Bas2HowZMWgfdDSPDHTObb_WxHXt0xw1Yo,248
 tuieval/templates/packs/answer/tests.yaml,sha256=WiYPOknPcO9E6f1wXhLcfA0W5v-oK8MgZV956uWtcUQ,2660
@@ -42,8 +42,8 @@ tuieval/templates/packs/tool_call/pack.toml,sha256=n4bx0lGJHSmW41uVqhfIXJ2BWZpmT
 tuieval/templates/packs/tool_call/system.txt,sha256=mKxu-lB-0YjLHXdgeFJa8x2C180OvcNz5cHv2N5Bg3U,254
 tuieval/templates/packs/tool_call/tests.yaml,sha256=Nv7c4syrzJ9cU8EBKSK_1ZSFx9V02aCjW4-2TBCPT7s,1859
 tuieval/templates/packs/tool_call/tools.yaml,sha256=HgxCkh0On2VwbHSsjAGM8tNCK7ZtKLGrs7lMCn3Fprs,1048
-tuieval-0.2.0.dev1.dist-info/METADATA,sha256=iCyaKWovBMfE2j3ZXID_ybu2Tmz0KvU-ORnIrIp-LJA,12067
-tuieval-0.2.0.dev1.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-tuieval-0.2.0.dev1.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
-tuieval-0.2.0.dev1.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
-tuieval-0.2.0.dev1.dist-info/RECORD,,
+tuieval-0.2.0.dev2.dist-info/METADATA,sha256=ukHZagdns1Pj_mnQQsl9dxLIl40A-E8BtYIPx57I-cw,12079
+tuieval-0.2.0.dev2.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+tuieval-0.2.0.dev2.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
+tuieval-0.2.0.dev2.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
+tuieval-0.2.0.dev2.dist-info/RECORD,,