Files

T

JustVugg f8e4dc95b5 serve: honor --ngen when the client omits max_tokens; convert: print the resolved plan (#382 , #383 )

Two operator-surprise fixes:

openai_server.py (#382, LordMZTE): a request without max_tokens defaulted to
min(256, limit) — so `coli serve --ngen 32768` still cut every answer at 256
tokens for clients that omit the field. The operator's configured budget IS the
default now; generation still ends at EOS, so it's a cap, not a target.

convert_fp8_to_int4.py (#383, bokiko): the resolved conversion plan (mode,
source, ebits/io/x bits, grouped-vs-per-row) prints as a [PLAN] line before any
work. The two traps in #383 — --mtp defaulting ebits to 8 with the grouped
branch silently gated off, and --mtp appearing to ignore --indir — are already
defused by the #355 fix (the --mtp pass emits ONLY head tensors on the local
path), but a 3.5-hour job must show its plan at second 1, not in a post-hoc
size sanity check. bokiko's exact invocation now prints:
  [PLAN] mode: MTP head only | source: local ./fp8 | experts 8-bit, ... |
         PER-ROW (grouped branch needs bits<=4; ebits=8 disables it)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-18 12:28:27 +02:00

expert_atlas

tools: one expert atlas, not two — retire expert_atlas.py, analyze.py gains --web for the dashboard

2026-07-15 14:16:36 +08:00

__init__.py

Organize project tools and local workflows: c/tools, c/scripts, c/tests, root Makefile (flat C core untouched) (#22 )

2026-07-10 10:08:39 +02:00

bench_ux.sh

GPU resident pipeline: batch CUDA attention, head-sharded kv_b, prefill expert groups, W4A16 mixed dispatch (#111 )

2026-07-14 18:18:05 +02:00

benchmark_cuda_fixture.py

profile effective CPU expert bandwidth

2026-07-18 05:34:41 +08:00

clean.py

Makefile: portable clean/test-c via python helpers — works without sh.exe on native Windows (#179 , fixes #172 )

2026-07-14 13:49:26 +02:00

convert_fp8_to_int4.py

serve: honor --ngen when the client omits max_tokens; convert: print the resolved plan (#382 , #383 )

2026-07-18 12:28:27 +02:00

convert_olmoe.py

convert_olmoe.py: wire --ebits through to quantization (#323 )

2026-07-16 21:59:16 +03:00

download_glm52.py

Translate user-facing runtime output to English, machine prefixes preserved, + CLI output test (#67 , #85 )

2026-07-12 13:38:40 +02:00

eval_glm.py

security: harden safetensors/JSON parsers against malicious model files

2026-07-15 08:13:20 +02:00

fetch_benchmarks.py

bench: survive transient hub errors — retry with backoff, per-task isolation, atomic writes (#304 )

2026-07-16 13:20:35 +03:00

gen_unicode.py

Translate user-facing runtime output to English, machine prefixes preserved, + CLI output test (#67 , #85 )

2026-07-12 13:38:40 +02:00

glm_fp8_emit.py

diskio: KV write batching + persistent handle; generators: unfuse experts

2026-07-15 02:32:12 -04:00

make_glm_bench_model.py

diskio: KV write batching + persistent handle; generators: unfuse experts

2026-07-15 02:32:12 -04:00

make_glm_oracle.py

Merge pull request #322 from woolcoxm/fix/oracle-transformers-pin

2026-07-16 19:46:20 +02:00

quant_ablation.py

tools: rate-scale the E8 lattice ball by bit-width — int3-e8 is now a real int3 codebook, not a fixed 2-bit ball

2026-07-17 18:39:53 +08:00

README.md

Organize project tools and local workflows: c/tools, c/scripts, c/tests, root Makefile (flat C core untouched) (#22 )

2026-07-10 10:08:39 +02:00

route_coupling_report.py

routing: cross-layer coupling trace dump + pair-table builder + opt-in coupled prefetch source (#176 )

2026-07-14 16:13:19 +02:00

route_pairs.py

routing: cross-layer coupling trace dump + pair-table builder + opt-in coupled prefetch source (#176 )

2026-07-14 16:13:19 +02:00

run_tests.py

run_tests: normpath test binaries — forward-slash relative paths fail CreateProcess on Windows (#196 )

2026-07-14 18:01:12 +02:00

README.md

Tools

These scripts support model preparation and offline engineering work. They are not runtime dependencies of the C engine.

convert_fp8_to_int4.py, download_glm52.py: model preparation
make_glm_oracle.py, make_glm_bench_model.py: deterministic fixtures
benchmark_cuda_fixture.py, eval_glm.py, fetch_benchmarks.py: benchmarks
gen_unicode.py: tokenizer table generation

Run them from c/, for example:

python3 tools/convert_fp8_to_int4.py --selftest
python3 tools/make_glm_bench_model.py --output /tmp/colibri-bench