Skip to content

Feature/speculative decoding ci #28

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
solderzzc merged 3 commits into from
Apr 12, 2026
Merged

Feature/speculative decoding ci #28

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a0f657b
docs: add SWIFTLM_TOP_K MoE expert tuning config to benchmark workflow
Apr 12, 2026
fee9492
ci: set SWIFTLM_TOP_K to 4 for realistic Speed Mode profile
Apr 12, 2026
087e8d9
test: reduce draft tokens to 1 and payload to 10 to squeeze under GPU…
Apr 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions .agents/workflows/run-benchmark.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,25 @@ The profiler will:
- **Different contexts**: Change `--contexts` (comma-separated list of token counts)
- **Output file**: Change `--out` path

## Expert Top-K Tuning for MoE Models

For Mixture of Expert (MoE) models (like `Qwen3.5-122B-A10B-4bit`), you can override the number of dynamically routed experts per token using the `SWIFTLM_TOP_K` environment variable. By default, SwiftLM evaluates the maximum number of experts defined by the model architecture. Reducing this trades marginal quality for extreme memory compression and streaming speed gains.

Provide the parameter securely when running the profiler:
```bash
SWIFTLM_TOP_K=6 python3 -u scripts/profiling/profile_runner.py ...
```

### Reference Pipeline (M1 Ultra 64GB, Qwen3.5-122B-A10B-4bit)

| Configuration | tok/s | vs. Original | Notes |
|---|---|---|---|
| Original `--stream-experts` | 0.58 | baseline | Sequential pread, 1 NVMe queue |
| `SWIFTLM_TOP_K=8` | 4.95 | 8.5× | All 8 experts evaluated (Full quality) |
| `SWIFTLM_TOP_K=6` | 5.20 | 9.0× | Recommended default |
| `SWIFTLM_TOP_K=4` | 5.91 | 10.2× | Best quality/speed tradeoff (Speed mode) |
| `SWIFTLM_TOP_K=2` | 6.52 | 11.2× | Still coherent output (Turbo mode) |

## After the Benchmark

4. Review the generated markdown file and check for any `FAILED / OOM` entries.
Expand Down
2 changes: 2 additions & 0 deletions .github/workflows/ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,7 @@ jobs:
- name: Run speculative decoding E2E
env:
HF_HUB_DOWNLOAD_TIMEOUT: "900"
SWIFTLM_TOP_K: "4"
run: |
chmod +x tests/test-speculative.sh
for attempt in 1 2 3; do
Expand Down Expand Up @@ -219,6 +220,7 @@ jobs:
- name: Run speculative evaluation E2E
env:
HF_HUB_DOWNLOAD_TIMEOUT: "900"
SWIFTLM_TOP_K: "4"
run: |
chmod +x tests/test-speculative-eval.sh
for attempt in 1 2 3; do
Expand Down
4 changes: 2 additions & 2 deletions tests/test-speculative-eval.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ PORT="${2:-15414}"
HOST="127.0.0.1"
MAIN_MODEL="${MAIN_MODEL:-mlx-community/Qwen3.5-9B-4bit}"
DRAFT_MODEL="${DRAFT_MODEL:-mlx-community/Qwen3.5-0.8B-MLX-4bit}"
NUM_DRAFT_TOKENS=2
NUM_DRAFT_TOKENS=1
URL="http://${HOST}:${PORT}"
PASS=0
FAIL=0
Expand Down Expand Up @@ -148,7 +148,7 @@ log "Test 3: Streaming speculative generation"

STREAM_OUTPUT=$(curl -sf -N --max-time 120 -X POST "$URL/v1/chat/completions" \
-H "Content-Type: application/json" \
-d "{\"model\":\"$MAIN_MODEL\",\"stream\":true,\"max_tokens\":30,\"messages\":[{\"role\":\"user\",\"content\":\"Name three fruits.\"}]}" \
-d "{\"model\":\"$MAIN_MODEL\",\"stream\":true,\"max_tokens\":10,\"messages\":[{\"role\":\"user\",\"content\":\"Name three fruits.\"}]}" \
2>/dev/null || true)

if echo "$STREAM_OUTPUT" | grep -q "data: \[DONE\]"; then
Expand Down
Loading