Prosecution Insights
Last updated: October 01, 2026
Application No. 18/983,599

LOOK AHEAD WINDOW SIZE FOR SPECULATIVE DECODING

Non-Final OA §102
Filed
Dec 17, 2024
Examiner
AZAD, ABUL K
Art Unit
2656
Tech Center
2600 — Communications
Assignee
Advanced Micro Devices Inc.
OA Round
1 (Non-Final)
86%
Grant Probability
Favorable
1-2
OA Rounds
7m
Est. Remaining
99%
With Interview

Examiner Intelligence

Grants 86% — above average
86%
Career Allowance Rate
689 granted / 806 resolved
+23.5% vs TC avg
Moderate +14% lift
Without
With
+14.0%
Interview Lift
resolved cases with interview
Typical timeline
2y 4m
Avg Prosecution
18 currently pending
Career history
821
Total Applications
across all art units

Statute-Specific Performance

§101
18.4%
-21.6% vs TC avg
§103
37.8%
-2.2% vs TC avg
§102
27.4%
-12.6% vs TC avg
§112
5.4%
-34.6% vs TC avg
Black line = Tech Center average estimate • Based on career data from 806 resolved cases

Office Action

§102
DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This action is in response to the communication filed on December 17, 2024. Claims 1-20 are pending in this action. 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. Claim(s) 1-5, 11-15, and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Fehlis et al. (US 2026/0093960). As per claim 1, Fehlis discloses, a method comprising: splitting an input dataset into a first set and a second set for speculative decoding using a draft model that generates look ahead tokens for a target model (Paragraph 0034); with the first set: computing an expected number of look ahead tokens accepted by the target model per call based on a first value indicative of a quantity of look ahead tokens generated by the draft model (Paragraph 0034); and modifying the quantity of look ahead tokens generated by the draft model to a second value based on the expected number of look ahead tokens accepted by the target model (Paragraphs 0034-0035); and with the second set, performing speculative decoding with a look ahead window size based on the second value (Paragraph 0034, “number of look ahead tokens” is claimed “look ahead window size”). As per claim 2, Fehlis discloses, further comprising: selecting the first value based on a historical data distribution of accepted tokens per call to the target model (Paragraph 0025). As per claim 3, Fehlis discloses, wherein the first value is selected to minimize clipping of the historical data distribution (Paragraph 0025). As per claim 4, Fehlis discloses, wherein computing the expected number of look ahead tokens accepted by the target model per call based on the first value comprises: computing an average number of look ahead tokens that are accepted by the target model based on the historical data distribution of accepted tokens per call to the target model (Paragraphs 0031-0036) As per claim 5, Fehlis discloses, wherein computing the expected number of look ahead tokens accepted by the target model per call based on the first value comprises: computing a percentage of look ahead tokens that are accepted by the target model based on the historical data distribution of accepted tokens per call to the target model (Paragraph 0025). As per claim 11, Fehlis discloses, wherein performing the speculative decoding with the look ahead window size based on the second value comprises multiple speculative decoding iterations (Paragraphs 0031-0036). As per claims 12-15 and 20, they are analyzed and thus rejected for the same reasons set forth in the rejections of claims 1-5 and 11, because the corresponding claims have similar limitations. Allowable Subject Matter Claims 6-10 and 16-19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Lott et al. (US 2024/0320433) discloses, Speculative decoding in autoregressive generative artificial intelligence model. Lee et al. (US 12,572,745) discloses, Suffix-based speculative token decoding for artificial intelligence model. Contact Information Any inquiry concerning this communication or earlier communications from the examiner should be directed to Abul K. Azad whose telephone number is (571) 272-7599. If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Bhavesh Mehta, can be reached at (571) 272-7453. Any response to this action should be mailed to: Commissioner for Patents P.O. Box 1450 Alexandria, VA 22313-1450 Or faxed to: (571) 273-8300. Hand-delivered responses should be brought to 401 Dulany Street, Alexandria, VA-22314 (Customer Service Window). Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). July 6, 2026 /ABUL K AZAD/Primary Examiner, Art Unit 2656
Read full office action

Prosecution Timeline

Dec 17, 2024
Application Filed
Jul 08, 2026
Non-Final Rejection mailed — §102 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12744041
DYNAMIC ASSISTANT SUGGESTIONS DURING ASSISTANT BROWSING
2y 0m to grant Granted Sep 22, 2026
Patent 12738270
METHOD FOR ANALYZING USER UTTERANCE AND ELECTRONIC DEVICE SUPPORTING THE SAME
3y 0m to grant Granted Sep 15, 2026
Patent 12731580
NATURAL LANGUAGE PROCESSING USING CONTEXT
2y 0m to grant Granted Sep 08, 2026
Patent 12718805
FOLLOW-UP QUERIES FOR LARGE LANGUAGE MODELS DURING VIRTUAL CONFERENCES
2y 10m to grant Granted Aug 25, 2026
Patent 12718811
ELECTRONIC DEVICES AND METHODS OF HANDLING USER UTTERANCES
2y 7m to grant Granted Aug 25, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

1-2
Expected OA Rounds
86%
Grant Probability
99%
With Interview (+14.0%)
2y 4m (~7m remaining)
Median Time to Grant
Low
PTA Risk
Based on 806 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month