mirror of
https://github.com/tiennm99/litellm.git
synced 2026-07-10 03:10:23 +00:00
Yassin Kortam
2eab9ee2c0
* perf: reduce per-request and per-chunk overhead across Anthropic streaming hot paths
- Introduce pure-text fast-path in `_build_complete_streaming_response` that collapses O(N) `content_block_delta` events into a single equivalent SSE event before conversion, eliminating per-output-token Pydantic `ModelResponseStream` construction; non-text streams (tool_use, thinking, citations) fall back to the unchanged legacy path
- Skip agentic streaming wrapper entirely when no callback overrides `async_should_run_agentic_loop`; the wrapper buffered every chunk and rebuilt the SSE response only to call hooks that all return `(False, {})` — a pure no-op for the default config
- Serialize request body once (`json.dumps`) for both the pre-call log input and the wire, instead of twice; avoids a full O(payload) scan per request, significant for long-context Claude Code histories
- Add fast path in `async_streaming_data_generator` that bypasses the per-chunk `async_post_call_streaming_hook` coroutine await, response-string materialization, and cost-injection call when no callback/guardrail/cost-injection is active (the default config)
- Resolve `_DD_STREAMING_TRACE_ENABLED` once at import time; eliminate per-chunk `NullSpan` context manager allocation when Datadog tracing is disabled (the default)
- Memoize `get_type_hints(AnthropicMessagesRequestOptionalParams)` with `@lru_cache(maxsize=1)` — resolves once per process instead of once per `/v1/messages` request (~80µs each)
- Hoist `cost_injection_active` out of the per-chunk loop in `chunk_processor`; eliminates repeated `getattr` + endpoint-type checks on every streamed byte chunk
- Extract `_build_passthrough_logging_result` from `_route_streaming_logging_to_handler` as a standalone static method to facilitate future off-loop dispatch
- Convert `async_sse_data_generator` from an `async for: yield` trampoline to a direct return of the underlying generator, removing one async-generator layer per streamed chunk
- Skip redundant `strip_empty_text_blocks_from_anthropic_messages` scan in `anthropic_messages_handler` when the async wrapper already sanitized (signalled via `_litellm_messages_presanitized` sentinel, popped before reaching provider params)
- Gate debug log `f-string` evaluation behind `isEnabledFor(DEBUG)` in both the streaming generator and the transformation layer to avoid serializing entire message payloads on every request at non-debug log levels
- Add benchmark script (`scripts/benchmark_anthropic_messages_perf.py`) with a local mock Anthropic SSE provider for reproducible TTFT and TPM measurement across commits/branches
- Add parity tests asserting fast-path and legacy-path produce byte-identical logged/billed payloads, plus unit tests for agentic hook detection, pre-serialized body reuse, and memoized key resolution
* perf: address greptile review for anthropic streaming hot path
- Bail to legacy in `_collapse_pure_text_chunks` when content_block_delta
events from different block indexes are observed without an intervening
flush. Anthropic sends blocks strictly sequentially, but defensive bail
prevents silent text-merging if the protocol ever interleaves.
- Replace leaf-class `__dict__` check for `async_post_call_streaming_hook`
in `_callback_capabilities` with a function-identity comparison that
walks the MRO. A vendor base class can carry the override and the
registered class can add nothing else; before this PR the hook was
unconditionally invoked, so an inherited-override miss would silently
drop the hook on the streaming path.
- Add unit tests for both behaviors.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(mypy): narrow model_name to str in cost-injection branch
The hoisted cost_injection_active flag in chunk_processor encodes the
`bool(model_name)` requirement but mypy can't track that invariant
through the local, so the per-chunk `_process_chunk_with_cost_injection(
chunk, model_name)` calls flagged Optional[str] vs str. Pin a typed
non-None local inside the cost-injection branch so mypy narrows
correctly without changing runtime behavior.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Yassin Kortam <yassinkortam@g.ucla.edu>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
litellm-proxy
A local, fast, and lightweight OpenAI-compatible server to call 100+ LLM APIs.
usage
$ uv tool install litellm
$ litellm --model ollama/codellama
#INFO: Ollama running on http://0.0.0.0:8000
replace openai base
import openai # openai v1.0.0+
client = openai.OpenAI(api_key="anything",base_url="http://0.0.0.0:8000") # set proxy to base_url
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
}
])
print(response)
See how to call Huggingface,Bedrock,TogetherAI,Anthropic, etc.
Folder Structure
Routes
proxy_server.py- all openai-compatible routes -/v1/chat/completion,/v1/embedding+ model info routes -/v1/models,/v1/model/info,/v1/model_group_inforoutes.health_endpoints/-/health,/health/liveliness,/health/readinessmanagement_endpoints/key_management_endpoints.py- all/key/*routesmanagement_endpoints/team_endpoints.py- all/team/*routesmanagement_endpoints/internal_user_endpoints.py- all/user/*routesmanagement_endpoints/ui_sso.py- all/sso/*routes