-
Notifications
You must be signed in to change notification settings - Fork 156
Add B300 config: kimi-k2.5-fp4-vllm #1056
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.
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
Merged
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,80 @@ | ||
| #!/usr/bin/env bash | ||
|
|
||
| # NOTE: At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/moonshotai/Kimi-K2.5.html | ||
| # does not have a B300-specific recipe, so this script reuses the existing | ||
| # Kimi-K2.5 FP4 B200 vLLM recipe as-is until B300-specific tuning is available. | ||
|
|
||
| source "$(dirname "$0")/../benchmark_lib.sh" | ||
|
|
||
| check_env_vars \ | ||
| MODEL \ | ||
| TP \ | ||
| CONC \ | ||
| ISL \ | ||
| OSL \ | ||
| MAX_MODEL_LEN \ | ||
| RANDOM_RANGE_RATIO \ | ||
| RESULT_FILENAME | ||
|
|
||
| if [[ -n "$SLURM_JOB_ID" ]]; then | ||
| echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME" | ||
| fi | ||
|
|
||
| hf download "$MODEL" | ||
|
|
||
| nvidia-smi | ||
|
|
||
| export TORCH_CUDA_ARCH_LIST="10.0" | ||
| export PYTHONNOUSERSITE=1 | ||
|
|
||
| SERVER_LOG=/workspace/server.log | ||
| PORT=${PORT:-8888} | ||
|
|
||
| if [ "${EVAL_ONLY}" = "true" ]; then | ||
| setup_eval_context | ||
| MAX_MODEL_LEN="$EVAL_MAX_MODEL_LEN" | ||
| fi | ||
| # Start GPU monitoring (power, temperature, clocks every second) | ||
| start_gpu_monitor | ||
|
|
||
| set -x | ||
| vllm serve $MODEL --host 0.0.0.0 --port $PORT \ | ||
| --tensor-parallel-size=$TP \ | ||
| --gpu-memory-utilization 0.90 \ | ||
| --max-model-len $MAX_MODEL_LEN \ | ||
| --max-num-seqs $CONC \ | ||
| --reasoning-parser kimi_k2 \ | ||
| --tool-call-parser kimi_k2 \ | ||
| --compilation_config.pass_config.fuse_allreduce_rms true \ | ||
| --no-enable-prefix-caching \ | ||
| --trust-remote-code > $SERVER_LOG 2>&1 & | ||
|
|
||
| SERVER_PID=$! | ||
|
|
||
| # Wait for server to be ready | ||
| wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID" | ||
|
|
||
| pip install -q datasets pandas | ||
|
|
||
| run_benchmark_serving \ | ||
| --model "$MODEL" \ | ||
| --port "$PORT" \ | ||
| --backend vllm \ | ||
| --input-len "$ISL" \ | ||
| --output-len "$OSL" \ | ||
| --random-range-ratio "$RANDOM_RANGE_RATIO" \ | ||
| --num-prompts $(( CONC * 10 )) \ | ||
| --max-concurrency "$CONC" \ | ||
| --result-filename "$RESULT_FILENAME" \ | ||
| --result-dir /workspace/ \ | ||
| --trust-remote-code | ||
|
|
||
| # After throughput, run evaluation only if RUN_EVAL is true | ||
| if [ "${RUN_EVAL}" = "true" ]; then | ||
| run_eval --framework lm-eval --port "$PORT" | ||
| append_lm_eval_summary | ||
| fi | ||
|
|
||
| # Stop GPU monitoring | ||
| stop_gpu_monitor | ||
| set +x | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🟡 The new
kimik2.5_fp4_b300.shscript carries overexport TORCH_CUDA_ARCH_LIST="10.0"from the B200 equivalent, but the B300 runner (launch_b300-nv.sh) never sets this variable — unlike the B200 Docker runner which explicitly passes-e TORCH_CUDA_ARCH_LIST="10.0". Every other B300 benchmark script (dsr1, qwen3.5) leaves it unset, letting PyTorch auto-detect the correct architecture; the new vLLM script is the sole exception. If B300 uses a different SM variant than B200 (e.g., SM 10.0a), hardcoding10.0could prevent B300-nativetorch.compilekernel optimizations from taking effect — remove this line to match B300 convention.Extended reasoning...
What the bug is: Line 27 of
kimik2.5_fp4_b300.shsetsexport TORCH_CUDA_ARCH_LIST="10.0", copied verbatim fromkimik2.5_fp4_b200.sh. While this value is correct for B200 (Blackwell SM 10.0), it was never verified for B300 and contradicts the established B300 scripting convention.The specific code path: The B300 single-node runner (
runners/launch_b300-nv.sh) usessrun --export=ALLwith Slurm/enroot and does not setTORCH_CUDA_ARCH_LISTanywhere. This contrasts with the B200 Docker runner (runners/launch_b200-dgxc.sh) and H100/H200 runners, which explicitly inject the architecture via-e TORCH_CUDA_ARCH_LIST="..."into the container environment. The benchmark scripts on B200/H100/H200 mirror that runner-level value redundantly; B300 scripts correctly reflect the runner convention of leaving it unset.Why existing code doesn't prevent it: A refutation argues this is a vLLM-specific convention (vLLM scripts set it; SGLang scripts don't). However, the true pattern is runner-level: B200/H100/H200 runners all set it; the B300 runner never does. All three pre-existing B300 single-node scripts (qwen3.5_fp8_b300.sh, qwen3.5_fp8_b300_mtp.sh, dsr1_fp4_b300.sh) — regardless of framework — leave
TORCH_CUDA_ARCH_LISTunset, consistent with the B300 runner's behavior. The new vLLM B300 script is the outlier.Impact: vLLM uses
torch.compilevia--compilation_config.pass_config.fuse_allreduce_rms true(present in this script). PyTorch compiles kernels for the arch list specified; if B300 has a distinct SM variant from exactly10.0(e.g.,sm_100a), the compiled kernels may be suboptimal or miss B300-specific optimizations. Impact is uncertain since B200 and B300 may share SM 10.0, but the inconsistency with infrastructure is clear.Fix: Remove line 27 (
export TORCH_CUDA_ARCH_LIST="10.0") to match the pattern of all other B300 scripts and the B300 runner itself.Step-by-step proof:
runners/launch_b200-dgxc.shpasses-e TORCH_CUDA_ARCH_LIST="10.0"to Docker — B200 vLLM scripts also set it (double-coverage, consistent).runners/launch_b300-nv.shusessrun --export=ALLwith noTORCH_CUDA_ARCH_LISTassignment anywhere in the file.benchmarks/single_node/dsr1_fp4_b300.sh,qwen3.5_fp8_b300.sh, andqwen3.5_fp8_b300_mtp.shall omitTORCH_CUDA_ARCH_LIST— consistent with the runner.benchmarks/single_node/kimik2.5_fp4_b300.shline 27 sets it to10.0— inconsistent with the runner and every other B300 script.TORCH_CUDA_ARCH_LISTand B300 reports a slightly different SM, PyTorch auto-detection would choose the correct architecture but is blocked by the hardcoded value.