minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[skill] Remove outdated llm-serving-auto-benchmark skill (#29487)

Browse Source
This commit is contained in:
Xiaoyu Zhang
2026-06-27 14:19:11 +08:00
committed by GitHub
parent 43435a2f8e
commit c36f166364
60 changed files with 563 additions and 6977 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/skills/llm-torch-profiler-analysis/scripts/analyze_llm_torch_profile.py
+20 -6
View File
@@ -34,8 +34,8 @@ def build_triage_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(
prog="analyze_llm_torch_profile.py",
description=(
"Compact LLM torch-profiler triage entrypoint for SGLang, vLLM, and "
"TensorRT-LLM. "
"Compact LLM torch-profiler triage entrypoint for SGLang, vLLM, "
"TensorRT-LLM, and TokenSpeed. "
"This prints three tables: kernel mapping, overlap opportunities, "
"and fuse opportunities. "
"Use either a single trace/profile input or a mapping+formal two-trace pair."
@@ -45,7 +45,17 @@ def build_triage_parser() -> argparse.ArgumentParser:
"--framework",
type=str,
default="auto",
choices=["auto", "sglang", "vllm", "trtllm", "tllm", "tensorrt-llm"],
choices=[
"auto",
"sglang",
"vllm",
"trtllm",
"tllm",
"tensorrt-llm",
"tokenspeed",
"token-speed",
"ts",
],
help=(
"Serving framework. Use auto to detect from trace contents, path hints, "
"or URL features."
@@ -64,7 +74,9 @@ def build_triage_parser() -> argparse.ArgumentParser:
help=(
"Running server URL for single-trace triage. SGLang supports direct "
"capture via sglang.profiler. vLLM and TensorRT-LLM require a server-side "
"torch-profiler output path exposed via --output-dir."
"torch-profiler output path exposed via --output-dir. TokenSpeed live "
"capture uses the server's /start_profile and /stop_profile endpoints "
"when they are available."
),
)
parser.add_argument(
@@ -74,7 +86,8 @@ def build_triage_parser() -> argparse.ArgumentParser:
help=(
"Trace output dir when using --url. For vLLM this should match the "
"server's torch_profiler_dir. For TensorRT-LLM it should match the "
"directory or file path configured by TLLM_TORCH_PROFILE_TRACE."
"directory or file path configured by TLLM_TORCH_PROFILE_TRACE. "
"For TokenSpeed this is passed as start_profile.output_dir."
),
)
parser.add_argument(
@@ -83,7 +96,8 @@ def build_triage_parser() -> argparse.ArgumentParser:
default="triage-trace",
help=(
"Profile prefix when generating a trace from --url. SGLang uses it "
"directly; vLLM and TensorRT-LLM may ignore it on the HTTP profiler path."
"directly; TokenSpeed maps it to profile_id; vLLM and TensorRT-LLM may "
"ignore it on the HTTP profiler path."
),
)
parser.add_argument(
.claude/skills/llm-torch-profiler-analysis/scripts/analyze_sglang_torch_profile.py
+1 -1
View File
@@ -1,7 +1,7 @@
"""Backwards-compatibility shim for the unified LLM torch-profiler entrypoint.
The real implementation now lives in ``analyze_llm_torch_profile`` because this
skill covers SGLang, vLLM, and TensorRT-LLM. Older scripts and runbooks that
skill covers SGLang, vLLM, TensorRT-LLM, and TokenSpeed. Older scripts and runbooks that
still invoke ``analyze_sglang_torch_profile.py`` keep working by forwarding to
that module.
"""
.claude/skills/llm-torch-profiler-analysis/scripts/probe_llm_server.py
+3 -3
View File
@@ -31,7 +31,7 @@ def parse_args() -> argparse.Namespace:
parser.add_argument(
"--framework",
required=True,
choices=("sglang", "vllm", "trtllm"),
choices=("sglang", "vllm", "trtllm", "tokenspeed"),
help="Serving framework.",
)
parser.add_argument(
@@ -42,7 +42,7 @@ def parse_args() -> argparse.Namespace:
parser.add_argument(
"--model",
default=None,
help="OpenAI model id. Auto-discovered for vLLM and TensorRT-LLM when omitted.",
help="OpenAI model id. Auto-discovered for vLLM, TensorRT-LLM, and TokenSpeed when omitted.",
)
parser.add_argument(
"--requests",
@@ -153,7 +153,7 @@ def openai_request(
def run_probe(args: argparse.Namespace) -> Dict[str, Any]:
prompts = args.prompt or list(DEFAULT_PROMPTS)
model = args.model
if args.framework in {"vllm", "trtllm"} and not model:
if args.framework in {"vllm", "trtllm", "tokenspeed"} and not model:
model = discover_openai_model(args.url, timeout=args.timeout)
latencies: List[float] = []
.claude/skills/llm-torch-profiler-analysis/scripts/profile_common.py
+82 -12
View File
@@ -22,6 +22,7 @@ FRAMEWORK_LABELS = {
"sglang": "SGLang",
"vllm": "vLLM",
"trtllm": "TensorRT-LLM",
"tokenspeed": "TokenSpeed",
}
TRACE_FILE_PATTERNS = (
"*.trace.json",
@@ -89,6 +90,9 @@ def canonicalize_framework(value: object) -> str:
"trtllm": "trtllm",
"tensorrt-llm": "trtllm",
"tensorrtllm": "trtllm",
"tokenspeed": "tokenspeed",
"token-speed": "tokenspeed",
"ts": "tokenspeed",
}
return aliases.get(lowered, "auto")
@@ -105,6 +109,8 @@ def _normalize_repo_relative_path_cached(text: str) -> str:
("python/sglang/", "python/sglang/"),
("sgl_kernel/", "sgl_kernel/"),
("vllm/", "vllm/"),
("python/tokenspeed/", "python/tokenspeed/"),
("tokenspeed/", "tokenspeed/"),
("tensorrt_llm/", "tensorrt_llm/"),
("tensorrt-llm/", "tensorrt_llm/"),
):
@@ -312,6 +318,8 @@ def detect_framework_from_text(text: object) -> Optional[str]:
lowered = normalize_text(text).lower()
if not lowered:
return None
if any(token in lowered for token in ("tokenspeed", "token-speed", "/ts/")):
return "tokenspeed"
if any(
token in lowered
for token in (
@@ -333,6 +341,22 @@ def detect_framework_from_server_args(server_args: Optional[dict]) -> Optional[s
if not isinstance(server_args, dict) or not server_args:
return None
lowered_keys = {normalize_text(key).lower() for key in server_args}
text = json.dumps(server_args, sort_keys=True)
if any(token in text.lower() for token in ("tokenspeed", "token-speed")):
return "tokenspeed"
if lowered_keys & {
"attn_tp_size",
"dense_tp_size",
"moe_tp_size",
"enable_mla_l1_5_cache",
"mla_chunk_multiplier",
"comm_fusion_max_num_tokens",
"enable_allreduce_fusion",
}:
return "tokenspeed"
text_hint = detect_framework_from_text(text)
if text_hint:
return text_hint
if lowered_keys & {
"attention_backend",
"sampling_backend",
@@ -342,7 +366,7 @@ def detect_framework_from_server_args(server_args: Optional[dict]) -> Optional[s
"schedule_policy",
}:
return "sglang"
return detect_framework_from_text(json.dumps(server_args, sort_keys=True))
return None
def detect_framework_from_trace(trace: object) -> Optional[str]:
@@ -402,6 +426,9 @@ def detect_framework_from_url(
or "decode" in server_info
):
return "sglang"
readiness = try_get_json(url.rstrip("/") + "/readiness", timeout=5.0)
if readiness is not None:
return "tokenspeed"
models = try_get_json(url.rstrip("/") + "/v1/models")
if isinstance(models, dict) and isinstance(models.get("data"), list):
return "vllm"
@@ -794,9 +821,11 @@ def wait_for_profiler_artifact(path: Path, timeout_s: float = 60.0) -> Path:
return path
def start_remote_profiler(url: str, framework: str) -> None:
def start_remote_profiler(
url: str, framework: str, payload: Optional[dict] = None
) -> None:
try:
post_json(url.rstrip("/") + "/start_profile", timeout=60.0)
post_json(url.rstrip("/") + "/start_profile", payload=payload, timeout=60.0)
except Exception as exc:
if framework == "vllm":
raise RuntimeError(
@@ -808,11 +837,40 @@ def start_remote_profiler(url: str, framework: str) -> None:
raise RuntimeError(
"TensorRT-LLM live torch profiling requires "
"a server build that exposes POST /start_profile plus the env vars "
"TLLM_PROFILE_START_STOP=1 and TLLM_TORCH_PROFILE_TRACE=/shared/path."
"TLLM_PROFILE_START_STOP=<start>-<stop> and "
"TLLM_TORCH_PROFILE_TRACE=/shared/path."
) from exc
if framework == "tokenspeed":
raise RuntimeError(
"TokenSpeed live torch profiling requires a server build that "
"exposes POST /start_profile and POST /stop_profile. The helper "
"passes output_dir, activities, and profile_id in the start payload."
) from exc
raise
def build_remote_profiler_start_payload(
framework: str,
output_path: Path,
profile_prefix: Optional[str],
stage: Optional[str],
) -> Optional[dict]:
if framework != "tokenspeed":
return None
profile_id = profile_prefix or "triage-trace"
if stage:
profile_id = f"{profile_id}-{stage}"
return {
"output_dir": str(output_path),
"activities": ["CPU", "GPU"],
"with_stack": True,
"record_shapes": False,
"profile_id": profile_id,
}
def stop_remote_profiler(url: str, framework: str) -> None:
try:
post_json(url.rstrip("/") + "/stop_profile", timeout=300.0)
@@ -829,6 +887,7 @@ def run_remote_profiler(
framework: str,
probe_plan: ProbePlan,
probe_delay: float,
profile_prefix: Optional[str] = None,
stage: Optional[str] = None,
) -> Path:
framework = canonicalize_framework(framework)
@@ -843,7 +902,11 @@ def run_remote_profiler(
if output_path.exists()
else set()
)
model = discover_openai_model(url) if framework in {"vllm", "trtllm"} else None
model = (
discover_openai_model(url)
if framework in {"vllm", "trtllm", "tokenspeed"}
else None
)
if probe_plan.warmup_requests > 0:
send_probe_requests(
url=url,
@@ -854,13 +917,18 @@ def run_remote_profiler(
model=model,
)
start_remote_profiler(url, framework)
start_payload = build_remote_profiler_start_payload(
framework=framework,
output_path=output_path,
profile_prefix=profile_prefix,
stage=stage,
)
start_remote_profiler(url, framework, payload=start_payload)
stop_error: Optional[BaseException] = None
try:
if probe_plan.capture_requests > 0:
# `sglang.profiler` performs its own startup work before it reaches
# POST /start_profile. A very short delay can send probes too early
# and miss the profiling window entirely.
# Server-side profilers may do setup work after POST /start_profile.
# A very short delay can send probes too early and miss the window.
time.sleep(max(5.0, probe_delay))
send_probe_requests(
url=url,
@@ -1064,14 +1132,14 @@ def run_profiler(
if profile_by_stage:
raise ValueError(
"--profile-by-stage is only supported for SGLang live capture. "
"Disable it when profiling vLLM or TensorRT-LLM."
"Disable it when profiling vLLM, TensorRT-LLM, or TokenSpeed."
)
if merge_profiles:
raise ValueError(
"--merge-profiles is only supported for SGLang live capture. "
"Disable it when profiling vLLM or TensorRT-LLM."
"Disable it when profiling vLLM, TensorRT-LLM, or TokenSpeed."
)
if profile_prefix:
if profile_prefix and resolved_framework in {"vllm", "trtllm"}:
print(
f"Note: {framework_display_name(resolved_framework)} ignores "
"--profile-prefix on the HTTP profiler control path.",
@@ -1093,6 +1161,7 @@ def run_profiler(
warmup_steps=warmup_steps,
),
probe_delay=probe_delay,
profile_prefix=profile_prefix,
)
output_root = ensure_remote_profiler_output_path(output_dir, resolved_framework)
for stage in stages:
@@ -1116,6 +1185,7 @@ def run_profiler(
warmup_steps=warmup_steps,
),
probe_delay=probe_delay,
profile_prefix=profile_prefix,
stage=stage,
)
return output_root
.claude/skills/llm-torch-profiler-analysis/scripts/render_triage_markdown_bundle.py
+4 -1
View File
@@ -12,9 +12,10 @@ FRAMEWORK_LABELS = {
"sglang": "SGLang",
"vllm": "vLLM",
"trtllm": "TensorRT-LLM",
"tokenspeed": "TokenSpeed",
}
FRAMEWORK_ORDER = {"sglang": 0, "vllm": 1, "trtllm": 2}
FRAMEWORK_ORDER = {"sglang": 0, "vllm": 1, "trtllm": 2, "tokenspeed": 3}
def parse_args(argv: Optional[Sequence[str]] = None) -> argparse.Namespace:
@@ -75,6 +76,8 @@ def framework_key_from_path(path: Path) -> str:
return "vllm"
if "trtllm" in lowered or "tensorrt" in lowered:
return "trtllm"
if "tokenspeed" in lowered or "token-speed" in lowered:
return "tokenspeed"
return "other"
.claude/skills/llm-torch-profiler-analysis/scripts/triage_kernel_helpers.py
+199 -9
View File
@@ -530,16 +530,16 @@ FUSION_PATTERN_REGISTRY: Tuple[FusionPatternSpec, ...] = (
likely_share=0.5,
),
FusionPatternSpec(
pattern="DSA fused metadata copy for graph replay",
pattern="NSA fused metadata copy for graph replay",
candidate_path="python/sglang/jit_kernel/fused_metadata_copy.py",
active_keywords=(
"fused_metadata_copy",
"fused_metadata_copy_multi",
"fused_dsa_cache_seqlens",
"fused_nsa_cache_seqlens",
"fused_flashmla_metadata",
),
rationale_hint=(
"DSA replay metadata copies are already fused into one-kernel" " families."
"NSA replay metadata copies are already fused into one-kernel" " families."
),
min_share=0.02,
likely_share=0.2,
@@ -744,23 +744,23 @@ FUSION_PATTERN_REGISTRY: Tuple[FusionPatternSpec, ...] = (
likely_share=1.5,
),
FusionPatternSpec(
pattern="DSA fused top-k transform / page-table build",
candidate_path="python/sglang/srt/layers/attention/dsa_backend.py",
pattern="NSA fused top-k transform / page-table build",
candidate_path="python/sglang/srt/layers/attention/nsa_backend.py",
active_keywords=(
"fast_topk_transform_fused",
"fast_topk_transform_ragged_fused",
),
rationale_hint=(
"DSA top-k metadata preparation already has fused transform kernels."
"NSA top-k metadata preparation already has fused transform kernels."
),
min_share=0.05,
likely_share=0.3,
),
FusionPatternSpec(
pattern="DSA fused quantize + indexed K-cache store",
pattern="NSA fused quantize + indexed K-cache store",
candidate_path=(
"python/sglang/jit_kernel/fused_store_index_cache.py"
"<br>python/sglang/srt/layers/attention/dsa/dsa_indexer.py"
"<br>python/sglang/srt/layers/attention/nsa/nsa_indexer.py"
),
active_keywords=("fused_store_index_k_cache",),
split_groups=(
@@ -768,7 +768,7 @@ FUSION_PATTERN_REGISTRY: Tuple[FusionPatternSpec, ...] = (
("index_k", "cache", "store"),
),
rationale_hint=(
"DSA already has a fused quantize-and-indexed-store kernel family."
"NSA already has a fused quantize-and-indexed-store kernel family."
),
min_share=0.2,
likely_share=1.0,
@@ -855,6 +855,180 @@ FUSION_PATTERN_REGISTRY: Tuple[FusionPatternSpec, ...] = (
likely_share=1.0,
priority=90,
),
FusionPatternSpec(
pattern="SGLang LTX2 fused Ada values",
candidate_path=(
"PR #29390"
"<br>python/sglang/jit_kernel/diffusion/triton/ltx2_ada_values.py"
"<br>python/sglang/multimodal_gen/runtime/models/dits/ltx_2.py"
),
active_keywords=(
"ltx2_ada_values9",
"ltx2_ada_values",
"LTX2TransformerBlock",
),
split_groups=(
("scale_shift_table", "timestep", "reshape"),
("get_ada_values", "ada", "adaln"),
("slice", "split", "unbind"),
),
rationale_hint=(
"SGLang mainline fuses LTX-2.3 Ada value materialization for"
" video/audio streams; split Ada table add/reshape/slice ladders"
" should be checked against this diffusion Triton kernel first."
),
origin="upstream",
model_include=("ltx", "ltx-2", "ltx2"),
min_share=0.2,
likely_share=1.0,
),
FusionPatternSpec(
pattern="SGLang LTX2 residual-gate add CUDA fast path",
candidate_path=(
"PR #29361"
"<br>python/sglang/jit_kernel/diffusion/residual_gate_add.py"
"<br>python/sglang/jit_kernel/csrc/diffusion/residual_gate_add.cuh"
"<br>python/sglang/multimodal_gen/runtime/models/dits/ltx_2.py"
),
active_keywords=(
"diffusion_residual_gate_add",
"residual_gate_add",
"_ltx2_residual_gate_add",
),
split_groups=(
("add", "mul", "gate"),
("residual", "update", "gate"),
("hidden_states", "attn_hidden_states", "gate"),
),
rationale_hint=(
"SGLang mainline fuses LTX2 residual + update * gate sites into"
" a CUDA custom op; split add/mul gate ladders should be checked"
" against this path before proposing a new diffusion elementwise"
" fusion."
),
origin="upstream",
model_include=("ltx", "ltx-2", "ltx2"),
min_share=0.2,
likely_share=1.0,
),
FusionPatternSpec(
pattern="TokenSpeed CuTe DSL MLA prefill / decode",
candidate_path=(
"python/tokenspeed/runtime/layers/attention/backends/tokenspeed_mla.py"
"<br>tokenspeed-mla/python/tokenspeed_mla/mla_decode.py"
"<br>tokenspeed-mla/python/tokenspeed_mla/mla_prefill.py"
"<br>tokenspeed-kernel/python/tokenspeed_kernel/ops/attention/"
"tokenspeed_mla/__init__.py"
),
active_keywords=(
"tokenspeed_mla_decode",
"tokenspeed_mla_prefill",
"BlackwellMultiHeadLatentAttentionForward",
),
split_groups=(
("mla", "flashmla", "attention", "fmha"),
("prefill", "decode", "verify"),
("fp8", "kv_cache", "page_table"),
),
rationale_hint=(
"TokenSpeed ships Blackwell CuTe DSL MLA prefill/decode kernels;"
" split MLA support kernels should be checked against backend"
" selection before being called novel."
),
origin="upstream",
model_include=("deepseek", "kimi", "qwen3.5", "qwen3_5"),
min_share=0.4,
likely_share=2.0,
),
FusionPatternSpec(
pattern="TokenSpeed MLA KV pack + FP8 quantize",
candidate_path=(
"tokenspeed-mla/python/tokenspeed_mla/mla_kv_pack_quantize_fp8.py"
"<br>tokenspeed-kernel/python/tokenspeed_kernel/ops/attention/"
"tokenspeed_mla/__init__.py"
),
active_keywords=(
"_mla_kv_pack_quantize_fp8_kernel",
"mla_kv_pack_quantize_fp8",
),
split_groups=(
("k_nope", "k_pe", "cat", "concat", "pack"),
("quant", "fp8", "float8"),
("v", "kv", "cache"),
),
rationale_hint=(
"TokenSpeed fuses MLA K/V pack, concat, and FP8 quantization into"
" one Triton kernel for chunked prefill."
),
origin="upstream",
model_include=("deepseek", "kimi", "qwen3.5", "qwen3_5"),
min_share=0.2,
likely_share=1.0,
),
FusionPatternSpec(
pattern="TokenSpeed fused top-k + top-p sampling",
candidate_path=(
"tokenspeed-kernel/python/tokenspeed_kernel/thirdparty/cuda/" # codespell:ignore thirdparty
"fused_topk_topp.py"
"<br>tokenspeed-kernel/python/tokenspeed_kernel/thirdparty/cuda/" # codespell:ignore thirdparty
"csrc/fused_topk_topp/fused_topk_topp.cu"
),
active_keywords=("fused_topk_topp", "fused_topk_topp_renorm"),
split_groups=(
("topk", "top_k"),
("topp", "top_p"),
("sampling", "renorm", "softmax"),
),
rationale_hint=(
"TokenSpeed has a fused top-k/top-p renormalization path for"
" decode sampling."
),
origin="upstream",
min_share=0.1,
likely_share=0.8,
),
FusionPatternSpec(
pattern="TokenSpeed persistent lm_head GEMM",
candidate_path=(
"tokenspeed-kernel/python/tokenspeed_kernel/thirdparty/cuda/" # codespell:ignore thirdparty
"lm_head_gemm.py"
"<br>tokenspeed-kernel/python/tokenspeed_kernel/thirdparty/cuda/" # codespell:ignore thirdparty
"csrc/lm_head_gemm.cu"
),
active_keywords=("lm_head_gemm",),
split_groups=(
("lm_head", "logits", "vocab"),
("gemm", "matmul", "linear"),
),
rationale_hint=(
"TokenSpeed has a shape-gated persistent lm_head GEMM path; visible"
" lm_head matmul ladders should be compared against it."
),
origin="upstream",
model_include=("kimi", "qwen"),
min_share=0.2,
likely_share=1.0,
),
FusionPatternSpec(
pattern="TokenSpeed NVFP4 GEMM + SwiGLU + quant",
candidate_path=(
"tokenspeed-kernel/python/tokenspeed_kernel/thirdparty/cute_dsl/" # codespell:ignore thirdparty
"nvfp4_gemm_swiglu_nvfp4_quant.py"
),
active_keywords=("nvfp4_gemm_swiglu_nvfp4_quant",),
split_groups=(
("gemm", "nvfp4", "fp4"),
("swiglu", "silu", "activation", "mul"),
("quant", "scale", "sfc"),
),
rationale_hint=(
"TokenSpeed's CuTe DSL kernel fuses NVFP4 GEMM, SwiGLU, and"
" optional output quantization in one expert-style path."
),
origin="upstream",
min_share=0.3,
likely_share=1.5,
),
FusionPatternSpec(
pattern="vLLM-origin Attention + Quantization",
candidate_path=(
@@ -1235,6 +1409,8 @@ def source_location_priority(location: str) -> int:
return 290 - penalty
if text.startswith("vllm/"):
return 285 - penalty
if text.startswith("python/tokenspeed/") or text.startswith("tokenspeed/"):
return 283 - penalty
if text.startswith("tensorrt_llm/"):
return 280 - penalty
if text.startswith("sgl_kernel/"):
@@ -1254,6 +1430,8 @@ def is_preferred_source_location(location: str) -> bool:
text.startswith("python/sglang/")
or text.startswith("sglang/")
or text.startswith("vllm/")
or text.startswith("python/tokenspeed/")
or text.startswith("tokenspeed/")
or text.startswith("tensorrt_llm/")
or text.startswith("sgl_kernel/")
)
@@ -1316,6 +1494,10 @@ def frame_priority(frame_name: str) -> int:
return 290 - penalty
if normalized_text.startswith("vllm/"):
return 285 - penalty
if normalized_text.startswith("python/tokenspeed/") or normalized_text.startswith(
"tokenspeed/"
):
return 283 - penalty
if normalized_text.startswith("tensorrt_llm/"):
return 280 - penalty
if normalized_text.startswith("sgl_kernel/"):
@@ -1329,6 +1511,8 @@ def frame_priority(frame_name: str) -> int:
return 120
if "/vllm/" in raw_text:
return 118
if "/tokenspeed/" in raw_text or "/TokenSpeed/" in raw_text:
return 117
if "/TensorRT-LLM/" in raw_text or "/tensorrt_llm/" in raw_text:
return 116
return 100
@@ -1336,6 +1520,10 @@ def frame_priority(frame_name: str) -> int:
return 110
if ".py(" in raw_text and "/vllm/" in raw_text:
return 108
if ".py(" in raw_text and (
"/tokenspeed/" in raw_text or "/TokenSpeed/" in raw_text
):
return 107
if ".py(" in raw_text and (
"/TensorRT-LLM/" in raw_text or "/tensorrt_llm/" in raw_text
):
@@ -2438,6 +2626,8 @@ def fusion_framework_hints(spec: FusionPatternSpec) -> set[str]:
hints: set[str] = set()
if "vllm/" in text:
hints.add("vllm")
if any(token in text for token in ("tokenspeed/", "tokenspeed-", "tokenspeed_")):
hints.add("tokenspeed")
if "tensorrt_llm/" in text:
hints.add("trtllm")
if any(token in text for token in ("python/sglang/", "sgl-kernel/", "sgl_kernel/")):
.claude/skills/llm-torch-profiler-analysis/scripts/triage_overlap_helpers.py
+10
View File
@@ -416,6 +416,10 @@ def is_meaningful_python_scope(name: str) -> bool:
return True
if normalized.startswith("vllm/"):
return True
if normalized.startswith("python/tokenspeed/") or normalized.startswith(
"tokenspeed/"
):
return True
if normalized.startswith("tensorrt_llm/"):
return True
if normalized.startswith("sgl_kernel/"):
@@ -697,6 +701,8 @@ def choose_best_scope(scope_chain: Sequence[str]) -> Optional[str]:
score += 48.0
elif scope.startswith("vllm/"):
score += 46.0
elif scope.startswith("python/tokenspeed/") or scope.startswith("tokenspeed/"):
score += 45.0
elif scope.startswith("tensorrt_llm/"):
score += 44.0
elif scope.startswith("sgl_kernel/"):
@@ -744,6 +750,10 @@ def source_scope_priority(scope: Optional[str]) -> int:
return 290 - penalty
if normalized.startswith("vllm/"):
return 285 - penalty
if normalized.startswith("python/tokenspeed/") or normalized.startswith(
"tokenspeed/"
):
return 283 - penalty
if normalized.startswith("tensorrt_llm/"):
return 280 - penalty
if normalized.startswith("sgl_kernel/"):