DETAILED ACTION
This office action is in response to the amendment filed on 08/10/2026.
Claims 1-6 are pending. Claims 1, 3 and 5 are independent.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-6 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Wei et al. (U.S. Publication 2024/0296283; hereinafter “Wei”).
In regard to independent claims 1, 3 and 5, Wei teaches at least one computer-readable medium having stored thereon instructions that, when executed, cause a computing device to perform operations comprising: managing workloads (Paragraph 0004, lines 6-11; “Clarification: physical volumes of originals are reduced means workloads has been managed;”) using an Infrastructure Processing Unit (IPU) (Paragraph 0017; “Note: processing apparatus being IPU wherein Examiner gave plain meaning of infrastructure processing unit and interpreted as any unit (software or hardware) that manages ‘infrastructure’ side of entities so that processor can run application more efficiently”);
optimizing (Paragraph 0005, lines 5-7; “Clarification: improve is equivalent to optimize”) an artificial intelligence (Al) model for an accelerator managed by the IPU (Paragraph 0018; “Note: computer program being the accelerator wherein Examiner interpreted accelerator as any subsystem (software or hardware) that optimizes execution for operations improving speed, efficiency and scalability and the accelerator (i.e. computer program) is being managed and controlled by the IPU (i.e. processing apparatus)”), wherein optimizing includes converting a high precision model to a compact low-precision model (Paragraph 0004, lines 4-6);
deploying the optimized Al model to the accelerator for execution of an inference; and storing, at a local memory, data relating to the Al model optimization (Paragraph 0003, lines 11-12; paragraph 0018; “Clarification: implements in paragraph 0018 means deployment”).
In regard to dependent claims 2, 4 and 6, Wei teaches optimizing includes converting a 32-bit floating point model to a 16-bit floating point model or an 8-bit integer type model (Paragraph 0004, lines 4-6).
Response to Arguments
Applicant’s arguments filed on 08/10/2026 have been considered but are not persuasive.
Applicant argues that “Such teachings of Wei do not disclose an Infrastructure Processing Unit, an accelerator managed by the IPU, or deployment of the optimized AI model by that IPU-managed arrangement to the accelerator for inference as recited by claim 1. “
In response, examiner respectfully disagrees.
First, the term “Infrastructure processing unit (IPU)” is broad and there is nothing in the claim that preclude examiner to give plain meaning and interpreted as any unit (software or hardware) that manages ‘infrastructure’ side of entities so that processor can run application more efficiently.
Second, the term “accelerator” is also broad and there is nothing in the claim that precludes examiners to give plain meaning and interpreted as any subsystem (software or hardware) that optimizes execution for operations improving speed, efficiency and scalability.
With said interpretation, the primary reference explicitly teaches accelerator is managed by IPU (see paragraph 0017-18 wherein processing apparatus being IPU and a computer program being accelerator which is managed and controlled by IPU).
Regarding deployment and storing issue in question, the primary reference explicitly teaches how optimized model is being deployed and stored (see Paragraph 0003, lines 11-12; paragraph 0018; “Clarification: implements in paragraph 0018 means deployment”)
For details, please see the rejection above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Sabat et al. U.S. Publication 2022/0261685 - Teaches optimizing model by means of converting high precision model (e.g. 16-bit floating point) to low precision model (e.g. 8-bit integer).
Lee et al. US Publication 2022/0283851 – Teaches managing workload wherein infrastructure processing unit manages and controls accelerators of heterogeneous types.
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REZA NABI whose telephone number is (571)270-7592. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, WILLIAM BASHORE can be reached at 571-272-4088. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Reza Nabi/
Primary Examiner, Art Unit 2174
