Skip to content

Minor inference changes for NemoRL #3666

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

Draft
ArEsKay3 wants to merge 1 commit into
base: main
Choose a base branch
from
+8 −5
Draft

Minor inference changes for NemoRL #3666

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 4 additions & 1 deletion megatron/core/inference/engines/dynamic_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -789,7 +789,10 @@ def _add_request(
self.failed_request_ids.append(request_id)
if self.rank == 0:
warnings.warn(
f"Request {request_id} failed to be added to the engine due to errors."
f"Request {request_id} failed to be added to the engine due to errors. " \
f"Prompt Tokens: {len(request.prompt_tokens)} " \
f"Tokens to generate: {request.sampling_params.num_tokens_to_generate} " \
f"Max sequence length: {self.context.max_sequence_length} "
)

return self.requests[request_id].future
Expand Down
6 changes: 3 additions & 3 deletions ...re/inference/text_generation_server/dynamic_text_gen_server/endpoints/chat_completions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ async def chat_completions():

try:
prompt_tokens = tokenizer.apply_chat_template(
messages, tokenize=True, add_generation_prompt=True, tools=req.get("tools", None)
messages, tokenize=True, add_generation_prompt=True, tools=req.get("tools", None), **req.get("chat_template_kwargs", {})
)
except (AttributeError, AssertionError):
warnings.warn(
Expand Down Expand Up @@ -184,15 +184,15 @@ async def chat_completions():
# Replicate data in the message field for compatibility.
message["prompt_token_ids"] = result["prompt_tokens"]
message["generation_token_ids"] = result["generated_tokens"]
message["generation_log_probs"] = result.get("generated_log_probs", None)
message["generation_log_probs"] = result.get("generated_log_probs", [])
return_log_probs = sampling_params.return_log_probs

choice_data = {
"index": request_idx,
"message": message,
"prompt_token_ids": result["prompt_tokens"],
"generation_token_ids": result["generated_tokens"],
"generation_log_probs": result["generated_log_probs"],
"generation_log_probs": result.get("generated_log_probs", []),
"raw_text": result["prompt"] + result["generated_text"],
# 'logprobs' in chat API is an object containing 'content'
# "logprobs": {"content": logprobs_content} if logprobs_content else None,
Expand Down
2 changes: 1 addition & 1 deletion megatron/core/inference/text_generation_server/dynamic_text_gen_server/flask_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ def health_check():
logger.info(f"Using parsers: {parsers}")

loop.set_default_executor(ThreadPoolExecutor(max_workers=8192))
await serve(AsyncioWSGIMiddleware(app, max_body_size=config.wsgi_max_body_size), config)
await serve(AsyncioWSGIMiddleware(app, max_body_size=config.wsgi_max_body_size), config, shutdown_trigger=lambda: asyncio.Future())


@trace_async_exceptions
Expand Down