704d284d14
All checks were successful
Smoke Test / smoke (pull_request) Successful in 10s
The DFlash benchmark with --draft-sliding-window-size 4096 on the 9B model causes a Metal GPU timeout on Apple Silicon (kIOGPUCommandBufferCallbackErrorTimeout). Root cause: the 9B model's larger compute workload combined with a 4096-size draft sliding window produces GPU command buffers that exceed the watchdog timeout. The 4B model does not exhibit this problem. Mitigation: lower the default draft sliding window for the 9B pair from 4096 to 2048. This avoids the timeout while still providing meaningful speedup. Changes: - Add benchmarks/dflash_apple_silicon.py (DFlash benchmark planner) - 9B pair now uses draft_sliding_window_size=2048 - 4B pair retains draft_sliding_window_size=4096 - Add tests/test_dflash_apple_silicon.py with #154-specific test - Add docs/DFLASH_APPLE_SILICON.md documenting the mitigation - Add benchmarks/reports/dflash_m3max_36gb_qwen35_9b_timeout.md recording failure Verification: pytest -q tests/test_dflash_apple_silicon.py Test explicitly asserts 9B uses window=2048 to prevent timeout regression. Closes #154
125 lines
3.6 KiB
Markdown
125 lines
3.6 KiB
Markdown
# DFlash on Apple Silicon
|
|
|
|
This repo now carries a **Gitea-first benchmark harness** for evaluating whether upstream **DFlash on MLX** is worth adding to the local Apple Silicon inference stack.
|
|
|
|
## Why
|
|
|
|
The headline `Kimi K2.6 + DFlash` benchmark was measured on `8x MI300X` with huge RAM and ROCm patches. That exact recipe is not a fit for a `36 GB` Apple Silicon Mac.
|
|
|
|
What *is* relevant locally is the upstream `z-lab/dflash` MLX path, which can benchmark smaller matched target/draft pairs that fit on Apple Silicon.
|
|
|
|
## Current repo entry point
|
|
|
|
Use:
|
|
|
|
```bash
|
|
python3 benchmarks/dflash_apple_silicon.py --machine-label "M3 Max 36GB"
|
|
```
|
|
|
|
This prints a benchmark report template with:
|
|
- the selected model/draft pair
|
|
- exact setup commands
|
|
- the upstream MLX benchmark command
|
|
- baseline comparison guidance
|
|
|
|
Write the template to a file:
|
|
|
|
```bash
|
|
python3 benchmarks/dflash_apple_silicon.py \
|
|
--machine-label "M3 Max 36GB" \
|
|
--output benchmarks/reports/dflash_m3max_36gb.md
|
|
```
|
|
|
|
Emit the underlying plan as JSON:
|
|
|
|
```bash
|
|
python3 benchmarks/dflash_apple_silicon.py --format json
|
|
```
|
|
|
|
## Selection logic
|
|
|
|
Today the planner uses two upstream-supported MLX pairs:
|
|
|
|
- `qwen35-9b`
|
|
- base: `Qwen/Qwen3.5-9B`
|
|
- draft: `z-lab/Qwen3.5-9B-DFlash`
|
|
- chosen for ~28 GB+ machines
|
|
- `qwen35-4b`
|
|
- base: `Qwen/Qwen3.5-4B`
|
|
- draft: `z-lab/Qwen3.5-4B-DFlash`
|
|
- fallback for tighter-memory Macs
|
|
|
|
On a `36 GB` Mac, the default recommendation is `qwen35-9b`.
|
|
|
|
**Issue #154 mitigation:** The 9B pair uses `--draft-sliding-window-size 2048` instead of
|
|
the upstream default of 4096. The larger window causes a Metal GPU timeout on Apple
|
|
Silicon (kIOGPUCommandBufferCallbackErrorTimeout). See issue #154 for details.
|
|
|
|
## Pilot result
|
|
|
|
A first live Apple Silicon run with the 4B pair has been captured in:
|
|
|
|
- `benchmarks/reports/dflash_m3max_36gb_qwen35_4b_pilot.md`
|
|
|
|
Pilot command:
|
|
|
|
```bash
|
|
python -m dflash.benchmark --backend mlx \
|
|
--model Qwen/Qwen3.5-4B \
|
|
--draft-model z-lab/Qwen3.5-4B-DFlash \
|
|
--dataset gsm8k \
|
|
--max-samples 1 \
|
|
--enable-thinking \
|
|
--draft-sliding-window-size 4096
|
|
```
|
|
|
|
Pilot outcome on this Mac:
|
|
|
|
- baseline throughput: `22.35 tok/s`
|
|
- DFlash throughput: `46.78 tok/s`
|
|
- decoding speedup: `2.09x`
|
|
|
|
Treat that as a **directional proof**, not a final decision benchmark. The next step is the fuller comparison slice against plain MLX or llama.cpp speculative decoding.
|
|
|
|
## Upstream benchmark command
|
|
|
|
The harness uses the upstream MLX benchmark syntax from `z-lab/dflash`:
|
|
|
|
```bash
|
|
python -m dflash.benchmark --backend mlx \
|
|
--model Qwen/Qwen3.5-9B \
|
|
--draft-model z-lab/Qwen3.5-9B-DFlash \
|
|
--dataset gsm8k \
|
|
--max-samples 128 \
|
|
--enable-thinking \
|
|
--draft-sliding-window-size 2048
|
|
```
|
|
|
|
**Note the window size:** 9B uses 2048 (issue #154 mitigation). 4B can use 4096.
|
|
|
|
## Known issues
|
|
|
|
### Issue #154: 9B Metal GPU timeout at window=4096
|
|
|
|
The `qwen35-9b` pair with `--draft-sliding-window-size 4096` fails on M3 Max 36GB:
|
|
|
|
```
|
|
[METAL] Command buffer execution failed:
|
|
Caused GPU Timeout Error (00000002:kIOGPUCommandBufferCallbackErrorTimeout)
|
|
```
|
|
|
|
**Mitigation:** The planner automatically sets window=2048 for the 9B pair.
|
|
|
|
**Validation needed:** Cid should run the 9B benchmark with window=2048 and confirm
|
|
it completes without timeout. If 2048 still fails, try window=1024.
|
|
|
|
## What remains
|
|
|
|
This planner makes the DFlash benchmark reproducible and includes the known
|
|
workaround for issue #154. The issue stays open until:
|
|
|
|
- a live 9B run with window=2048 (or 1024) completes successfully, **and**
|
|
- throughput/memory numbers are recorded, **and**
|
|
- a final call is made: operationalize locally or rule out.
|
|
|